# MiniMax M3 > Source: Benchize (https://benchize.com) — https://benchize.com/models/minimax-m3. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/minimax-m3. MiniMax Canonical URL: https://benchize.com/models/minimax-m3 Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. MiniMax ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Legal Research Bench / business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Abusiness_commercial.md) | 25.58% | SE ±6.73 pp | 34 / 50 | $0.35 | 867.94source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 25.581 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.34538 \| USD \| per_test \| Lower is better \| \| `latency` \| 867.939 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.73 pp sourcePopulation 82 stderr 6.733 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/business_commercial/minimax~1MiniMax-M3` | | | | | | | | | [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md) | 72.73% | SE ±0.86 pp | 25 / 40 | $0.00728 | 94.04source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.731 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00728 \| USD \| per_test \| Lower is better \| \| `latency` \| 94.036 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.86 pp sourcePopulation 145 stderr 0.863 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Adata_privacy_cybersecurity.md) | 0% | SE ±0 pp | 13 / 49 | $2.16 | 1,542.71source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.157888 \| USD \| per_test \| Lower is better \| \| `latency` \| 1542.712 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/data_privacy_cybersecurity/minimax~1MiniMax-M3` | | | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,485.82 | — | 54 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.823707405568 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1480.7827754229932 rank 85 upper 1490.864639388143 variance 6.614933659071511 votes 26455 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6785/row` | | | | | | | | | [Legal Research Bench / weighted pass immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__immigration.md) | 78.59% | SE ±8.75 pp | 26 / 50 | $0.48 | 882.27source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.593 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.482243 \| USD \| per_test \| Lower is better \| \| `latency` \| 882.27 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.75 pp sourcePopulation 82 stderr 8.748 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__immigration/minimax~1MiniMax-M3` | | | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,442.76 | — | 54 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1442.7560803080826 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1437.8512310627575 rank 88 upper 1447.6609295534079 variance 6.262606796607332 votes 27051 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1724/row` | | | | | | | | | [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,258.56 | — | 47 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1258.5648495261528 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision ### Reported statistics lower 1252.112132589012 rank 61 upper 1265.0175664632939 variance 10.838995760298879 votes 13947 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1079/row` | | | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,430.32 | — | 63 / 134 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1430.3242741236395 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1415.8070667659263 rank 107 upper 1444.8414814813523 variance 54.86179061233675 votes 2040 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10871/row` | | | | | | | | | [Legal Research Bench / immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aimmigration.md) | 27.27% | SE ±14.08 pp | 21 / 50 | $0.48 | 882.27source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.273 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.482243 \| USD \| per_test \| Lower is better \| \| `latency` \| 882.27 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.08 pp sourcePopulation 82 stderr 14.084 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/immigration/minimax~1MiniMax-M3` | | | | | | | | | [CyberBench v1.1 / poc](https://benchize.com/benchmarks/benchmark%3Acyber%3Apoc.md) | 55% | SE ±6.42 pp | 15 / 28 | $4.76 | 3,411.34source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.756365 \| USD \| per_test \| Lower is better \| \| `latency` \| 3411.342 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.42 pp sourcePopulation 47 stderr 6.423 tokenTotals {"cache_read_tokens":2126479900,"cache_write_tokens":0,"input_tokens":2166622902,"output_tokens":2549380,"reasoning_tokens":244908} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/poc/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aimmigration.md) | 0% | SE ±0 pp | 6 / 49 | $0.99 | 1,062.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.987413 \| USD \| per_test \| Lower is better \| \| `latency` \| 1062.394 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/immigration/minimax~1MiniMax-M3` | | | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,495.95 | — | 55 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495.9540199218593 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1490.3076442133492 rank 88 upper 1501.6003956303696 variance 8.299336301591078 votes 18701 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/897/row` | | | | | | | | | [Public Benefits Bench v1 / both](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench-v1%3Aboth.md) | 60.69% | SE ±1.27 pp | 3 / 8 | $0.2 | 705.54source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_snap_v1.BPa0Hrre.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.69 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.198621 \| USD \| per_test \| Lower is better \| \| `latency` \| 705.544 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.27 pp sourcePopulation 13 stderr 1.27 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_snap_v1.BPa0Hrre.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:18.363Z Evidence SHA-256 `b85e2b3cbdf03e13e2ffdb27ce4f108003a548d705a24ae26a0a115e2027475d` Source locator `/tasks/both/minimax~1MiniMax-M3` | | | | | | | | | [Legal Research Bench / criminal](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acriminal.md) | 26.32% | SE ±5.88 pp | 31 / 50 | $0.33 | 855.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 26.316 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.325282 \| USD \| per_test \| Lower is better \| \| `latency` \| 855.631 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.88 pp sourcePopulation 82 stderr 5.884 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/criminal/minimax~1MiniMax-M3` | | | | | | | | | [Tax Agent Bench / weighted pass fact pattern analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__fact_pattern_analysis.md) | 33.8% | SE ±6.56 pp | 38 / 46 | $0.17 | 368.23source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.802 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.166429 \| USD \| per_test \| Lower is better \| \| `latency` \| 368.229 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.56 pp sourcePopulation 73 stderr 6.56 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__fact_pattern_analysis/minimax~1MiniMax-M3` | | | | | | | | | [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,169elo | SE ±7.9 | 22 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1169 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion minimax-m3 variationName public ### Reported statistics Uncertainty Standard error: ±7.9 averageGenerationTimeMs Not reported battles 2191 losses 1188 standardError 7.9047 winRate 45.8 wins 1003 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label MiniMax M3 Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/27` | | | | | | | | | [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,233.61 | — | 47 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1233.6104262364424 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision ### Reported statistics lower 1216.5785524609848 rank 64 upper 1250.6423000118998 variance 75.51420901362127 votes 1339 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/426/row` | | | | | | | | | [MMLU Pro / philosophy](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphilosophy.md) | 80.16% | SE ±1.79 pp | 27 / 40 | $0.00228 | 23.04source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.16 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002277 \| USD \| per_test \| Lower is better \| \| `latency` \| 23.038 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.79 pp sourcePopulation 138 stderr 1.792 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/philosophy/minimax~1MiniMax-M3` | | | | | | | | | [MMLU Pro / physics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphysics.md) | 90.84% | SE ±0.85 pp | 26 / 40 | $0.00644 | 50.01source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.839 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006439 \| USD \| per_test \| Lower is better \| \| `latency` \| 50.009 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.85 pp sourcePopulation 138 stderr 0.847 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/physics/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent (v2) / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aprecedents.md) | 23.24% | SE ±1.57 pp | 32 / 50 | $0.57 | 804.14source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 23.24 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.571079 \| USD \| per_test \| Lower is better \| \| `latency` \| 804.141 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.57 pp sourcePopulation 80 stderr 1.574 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/precedents/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__structured_finance_securitization.md) | 81.27% | SE ±2.2 pp | 24 / 49 | $1.25 | 925.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.250112 \| USD \| per_test \| Lower is better \| \| `latency` \| 925.634 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.2 pp sourcePopulation 81 stderr 2.202 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__structured_finance_securitization/minimax~1MiniMax-M3` | | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,235elo | — | 35 / 99 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1235 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion minimax-m3 variationName public ### Reported statistics averageGenerationTimeMs 114109 battles 1393 losses 677 standardError Not reported winRate 51.4 wins 716 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label MiniMax M3 Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/53` | | | | | | | | | [LegalBench / conclusion tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aconclusion_tasks.md) | 89.28% | SE ±0.74 pp | 16 / 44 | $0.00109 | 9.22source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.276 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001085 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.224 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.74 pp sourcePopulation 151 stderr 0.742 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/conclusion_tasks/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent (v2) / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aoverall.md) | 48.27% | SE ±0.44 pp | 36 / 50 | $0.32 | 496.89source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.269 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.32345 \| USD \| per_test \| Lower is better \| \| `latency` \| 496.894 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.44 pp sourcePopulation 80 stderr 0.437 tokenTotals {"cache_read_tokens":126041678,"cache_write_tokens":0,"input_tokens":302569216,"output_tokens":10069655,"reasoning_tokens":null} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,482.37 | — | 45 / 90 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.367033184203 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1476.8517909613051 rank 66 upper 1487.8822754071007 variance 7.918319106629695 votes 19803 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/277/row` | | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,424.83 | — | 55 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.8310834936083 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1419.9048751554744 rank 91 upper 1429.7572918317421 variance 6.317268965625287 votes 49436 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2144/row` | | | | | | | | | [Code Migration v1.1 / cobol](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acobol.md) | 58.56% | SE ±13.46 pp | 16 / 17 | $7.12 | 4,337.7source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.556 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.118403 \| USD \| per_test \| Lower is better \| \| `latency` \| 4337.701 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±13.46 pp sourcePopulation 26 stderr 13.457 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/cobol/minimax~1MiniMax-M3` | | | | | | | | | [EMB v1.1 / ma](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Ama.md) | 70.61% | SE ±5.78 pp | 18 / 19 | $1.91 | 1,122.87source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.608 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.905749 \| USD \| per_test \| Lower is better \| \| `latency` \| 1122.869 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.78 pp sourcePopulation 30 stderr 5.78 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/ma/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__intellectual_property.md) | 90.46% | SE ±1.75 pp | 23 / 49 | $1.35 | 1,246.85source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.459 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.349078 \| USD \| per_test \| Lower is better \| \| `latency` \| 1246.85 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.75 pp sourcePopulation 81 stderr 1.749 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__intellectual_property/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent v2.1 / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Afinancial_modeling.md) | 16.23% | SE ±4.81 pp | 18 / 18 | $0.37 | 270.01source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 16.228 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.365806 \| USD \| per_test \| Lower is better \| \| `latency` \| 270.009 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.81 pp sourcePopulation 28 stderr 4.814 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/financial_modeling/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__banking_finance.md) | 86.62% | SE ±2.08 pp | 27 / 49 | $1.17 | 1,180.7source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.617 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.170507 \| USD \| per_test \| Lower is better \| \| `latency` \| 1180.702 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.08 pp sourcePopulation 81 stderr 2.08 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__banking_finance/minimax~1MiniMax-M3` | | | | | | | | | [MortgageTax / overall](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Aoverall.md) | 68.36% | SE ±0.91 pp | 12 / 31 | $0.00833 | 26.76source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.362 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008326 \| USD \| per_test \| Lower is better \| \| `latency` \| 26.756 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.91 pp sourcePopulation 98 stderr 0.91 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / capital markets](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acapital_markets.md) | 20% | SE ±20 pp | 4 / 49 | $0.94 | 931.2source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.941373 \| USD \| per_test \| Lower is better \| \| `latency` \| 931.196 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/capital_markets/minimax~1MiniMax-M3` | | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,470.4 | Range 1,424.8–1,513.6 | 82 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1470.4 \| rating \| reported \| Higher is better \| \| `overall` \| 74.79 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 62.85 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 73.03 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 70.85 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 78.23 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 92.81 \| source_score \| rubric \| Higher is better \| \| `slop` \| 78.49 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.14 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 74.43 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 70.89 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 70.91 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 72.6 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort unknown scoreScope 10_task_current sourceConfiguration minimax-m3-or ### Reported statistics Uncertainty Reported interval: 1,424.8–1,513.6 interval [1424.8,1513.6] rank 83 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label MiniMax M3 (thinking on) Evaluated 2026-10-08 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/82` | | | | | | | | | [Legal Research Bench / civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acivil_litigation.md) | 25.93% | SE ±8.59 pp | 32 / 50 | $0.39 | 823.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 25.926 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.385069 \| USD \| per_test \| Lower is better \| \| `latency` \| 823.116 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.59 pp sourcePopulation 82 stderr 8.594 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/civil_litigation/minimax~1MiniMax-M3` | | | | | | | | | [Legal Research Bench / weighted pass civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__civil_litigation.md) | 84.85% | SE ±2.96 pp | 30 / 50 | $0.39 | 823.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.854 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.385069 \| USD \| per_test \| Lower is better \| \| `latency` \| 823.116 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.96 pp sourcePopulation 82 stderr 2.956 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__civil_litigation/minimax~1MiniMax-M3` | | | | | | | | | [MortgageTax / semantic extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Asemantic_extraction.md) | 59.46% | SE ±1.38 pp | 15 / 31 | $0.00703 | 14.5source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.459 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007033 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.499 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.38 pp sourcePopulation 98 stderr 1.384 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/semantic_extraction/minimax~1MiniMax-M3` | | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,162elo | — | 34 / 77 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1162 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion minimax-m3 variationName public ### Reported statistics averageGenerationTimeMs 54735 battles 2608 losses 1429 standardError Not reported winRate 45.2 wins 1179 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label MiniMax M3 Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/60` | | | | | | | | | [Public Benefits Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Apublic-benefits-bench%3Aoverall.md) | 64.14% | SE ±1.25 pp | 16 / 34 | $0.25 | 691.44source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_snap.CUcEPb0v.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.141 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.2543 \| USD \| per_test \| Lower is better \| \| `latency` \| 691.436 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.25 pp sourcePopulation 50 stderr 1.247 tokenTotals {"cache_read_tokens":256756972,"cache_write_tokens":0,"input_tokens":284714117,"output_tokens":4543318,"reasoning_tokens":null} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_snap.CUcEPb0v.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:46:17.865Z Evidence SHA-256 `6f091831ab607a26d65d2ade18cba7ce345ea3a67297b8c378e8a06ce398360d` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [CyberBench v1.1 / overall](https://benchize.com/benchmarks/benchmark%3Acyber%3Aoverall.md) | 65% | SE ±6.1 pp | 18 / 28 | $3.41 | 2,456.4source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.408292 \| USD \| per_test \| Lower is better \| \| `latency` \| 2456.402 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.1 pp sourcePopulation 47 stderr 6.104 tokenTotals {"cache_read_tokens":1494349503,"cache_write_tokens":0,"input_tokens":1519598089,"output_tokens":2352544,"reasoning_tokens":498876} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Vals Multimodal Index / swebench](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aswebench.md) | 69.61% | SE ±4.55 pp | 16 / 20 | $0.51 | 765.23source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.608 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.508278 \| USD \| per_test \| Lower is better \| \| `latency` \| 765.232 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Not reported reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.55 pp sourcePopulation 33 stderr 4.554 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/swebench/minimax~1MiniMax-M3` | | | | | | | | | [SWE-bench Multimodal / prettier](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Aprettier.md) | 46.15% | SE ±14.39 pp | 12 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.154 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.39 pp sourcePopulation 20 stderr 14.391 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/prettier/minimax~1MiniMax-M3` | | | | | | | | | [Vals Multimodal Index / finance agent](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Afinance_agent.md) | 48.01% | SE ±1.42 pp | 15 / 20 | $0.29 | 502.94source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.008 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.291233 \| USD \| per_test \| Lower is better \| \| `latency` \| 502.942 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.42 pp sourcePopulation 33 stderr 1.421 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/finance_agent/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent v2.1 / adjustments](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aadjustments.md) | 59.5% | SE ±6.95 pp | 11 / 18 | $0.27 | 161.25source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.501 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.272319 \| USD \| per_test \| Lower is better \| \| `latency` \| 161.247 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.95 pp sourcePopulation 28 stderr 6.946 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/adjustments/minimax~1MiniMax-M3` | | | | | | | | | [Legal Research Bench / weighted pass criminal](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__criminal.md) | 78.11% | SE ±2.89 pp | 35 / 50 | $0.33 | 855.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.11 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.325282 \| USD \| per_test \| Lower is better \| \| `latency` \| 855.631 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.89 pp sourcePopulation 82 stderr 2.891 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__criminal/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aemployment_labor.md) | 0% | SE ±0 pp | 1 / 49 | $1.29 | 1,162.31source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.29091 \| USD \| per_test \| Lower is better \| \| `latency` \| 1162.312 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/employment_labor/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent (v2) / comparables](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Acomparables.md) | 41.67% | SE ±3.91 pp | 32 / 50 | $0.39 | 577.33source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.669 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.388805 \| USD \| per_test \| Lower is better \| \| `latency` \| 577.327 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.91 pp sourcePopulation 80 stderr 3.912 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/comparables/minimax~1MiniMax-M3` | | | | | | | | | [DesignArena Native Android development](https://benchize.com/benchmarks/designarena%3Aandroid.md) | 1,163elo | — | 16 / 23 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=android) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1163 \| elo \| android \| Higher is better \| ### Configuration arenaType agents category nativeapps inputModality Not reported sourceModelVersion minimax-m3 variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 1170 losses 652 standardError Not reported winRate 44.3 wins 518 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=android) Source designarena Original model label MiniMax M3 Source version public Observed 2026-10-21T16:38:03.000Z Evidence SHA-256 `d9d0cd4bea54b696c28f907a98ba42ebf8dd4da9da201b6c70c95f76de35f525` Source locator `/data/22` | | | | | | | | | [Rapidata SVG generation — Overall preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Aoverall.md) | 926.64elo | CI 918.61–934.67 | 25 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 926.6376776967184 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion overall participantId par_1MFltlQRYSJKls sourceModelVersion minimax-m3 weighted false ### Reported statistics Uncertainty Confidence interval: 918.61–934.67 confidenceIntervalLowerOffset 8.027469897077822 confidenceIntervalUpperOffset 8.027469897077935 totalMatches 40252.964471045365 wins 20444.45835194186 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) Source rapidata Original model label minimax-m3 Source version v1 Observed 2026-10-21T16:37:39.078Z Evidence SHA-256 `4b73ff7e4ca0ecfd64f7888c2d64f3398a058c945c4644acd54eddb330e16d66` Source locator `/items/46` | | | | | | | | | [Vibe Code Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Avibe-code%3Aoverall.md) | 47.57% | SE ±5.44 pp | 41 / 59 | $6.45 | 5,073.23source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.566 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.453899 \| USD \| per_test \| Lower is better \| \| `latency` \| 5073.23 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.44 pp sourcePopulation 116 stderr 5.442 tokenTotals {"cache_read_tokens":null,"cache_write_tokens":null,"input_tokens":61631839,"output_tokens":5567819,"reasoning_tokens":null} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:46:08.625Z Evidence SHA-256 `0e8c23f521a0f751c5592952620e197b376cade41c78578461b7aa5740a173e7` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Tax Agent Bench / weighted pass controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__controversy_precedence_analysis.md) | 52.43% | SE ±8.07 pp | 28 / 46 | $0.17 | 366.09source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.429 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.172383 \| USD \| per_test \| Lower is better \| \| `latency` \| 366.09 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.07 pp sourcePopulation 73 stderr 8.069 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__controversy_precedence_analysis/minimax~1MiniMax-M3` | | | | | | | | | [Terminal-Bench 2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aoverall.md) | 53.56% | SE ±0.75 pp | 33 / 43 | $0.21 | 1,023.42source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.558 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.205973 \| USD \| per_test \| Lower is better \| \| `latency` \| 1023.416 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.75 pp sourcePopulation 76 stderr 0.749 tokenTotals {"cache_read_tokens":53014239,"cache_write_tokens":0,"input_tokens":64485322,"output_tokens":2119689,"reasoning_tokens":0} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate tax](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__tax.md) | 84.95% | SE ±2.07 pp | 9 / 49 | $1.55 | 1,470.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.95 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.553621 \| USD \| per_test \| Lower is better \| \| `latency` \| 1470.598 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.07 pp sourcePopulation 81 stderr 2.071 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__tax/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__emerging_companies_venture_capital.md) | 83.28% | SE ±2.18 pp | 33 / 49 | $1.73 | 1,607.58source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.276 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.729985 \| USD \| per_test \| Lower is better \| \| `latency` \| 1607.58 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.18 pp sourcePopulation 81 stderr 2.184 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__emerging_companies_venture_capital/minimax~1MiniMax-M3` | | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,473.66 | — | 63 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.6611902248799 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1463.7889055302885 rank 105 upper 1483.533474919471 variance 25.371091983605037 votes 4220 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/521/row` | | | | | | | | | [Tax Agent Bench / weighted pass numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__numbers_calculations.md) | 54.9% | SE ±8.07 pp | 40 / 46 | $0.09 | 196.91source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.9 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.085401 \| USD \| per_test \| Lower is better \| \| `latency` \| 196.912 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.07 pp sourcePopulation 73 stderr 8.072 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__numbers_calculations/minimax~1MiniMax-M3` | | | | | | | | | [Terminal-Bench 4.0 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Aoverall.md) | 1.01% | SE ±1.01 pp | 34 / 36 | $7.23 | 4,582.92source duration | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 1.01 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.229497 \| USD \| per_test \| Lower is better \| \| `latency` \| 4582.924 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.01 pp sourcePopulation 52 stderr 1.01 tokenTotals {"cache_read_tokens":3254206054,"cache_write_tokens":0,"input_tokens":3308478889,"output_tokens":12669342,"reasoning_tokens":2749857} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [MMLU-Pro](https://benchize.com/benchmarks/mmlu-pro.md) | 84.22% | SE ±0.36 pp | 28 / 40 | $0.00481 | 41.39source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.22 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004811 \| USD \| per_test \| Lower is better \| \| `latency` \| 41.39 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.36 pp sourcePopulation 138 stderr 0.364 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Tax Agent Bench / numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Anumbers_calculations.md) | 19.4% | SE ±7.23 pp | 40 / 46 | $0.09 | 196.91source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 19.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.085401 \| USD \| per_test \| Lower is better \| \| `latency` \| 196.912 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.23 pp sourcePopulation 73 stderr 7.226 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/numbers_calculations/minimax~1MiniMax-M3` | | | | | | | | | [LegalBench / issue tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aissue_tasks.md) | 90.86% | SE ±0.55 pp | 12 / 44 | $0.0009 | 6.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.862 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.0009 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.976 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.55 pp sourcePopulation 151 stderr 0.553 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/issue_tasks/minimax~1MiniMax-M3` | | | | | | | | | [MMLU Pro / business](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abusiness.md) | 88.34% | SE ±1.16 pp | 30 / 40 | $0.00385 | 30.78source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.34 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003849 \| USD \| per_test \| Lower is better \| \| `latency` \| 30.784 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.16 pp sourcePopulation 138 stderr 1.164 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/business/minimax~1MiniMax-M3` | | | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,443.08 | — | 53 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.077039409174 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1436.5438589952391 rank 81 upper 1449.610219823109 variance 11.11099931387808 votes 11454 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9396/row` | | | | | | | | | [EMB v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Aoverall.md) | 59.75% | SE ±2.54 pp | 19 / 19 | $3.18 | 1,298.81source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.754 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.18384 \| USD \| per_test \| Lower is better \| \| `latency` \| 1298.806 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.54 pp sourcePopulation 30 stderr 2.537 tokenTotals {"cache_read_tokens":2146906887,"cache_write_tokens":0,"input_tokens":2167916385,"output_tokens":14444692,"reasoning_tokens":4485341} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [MMLU Pro / psychology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Apsychology.md) | 83.33% | SE ±1.32 pp | 28 / 40 | $0.0021 | 25.99source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002098 \| USD \| per_test \| Lower is better \| \| `latency` \| 25.992 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.32 pp sourcePopulation 138 stderr 1.323 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/psychology/minimax~1MiniMax-M3` | | | | | | | | | [Rapidata SVG generation — Alignment](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkk9yZHssERh.md) | 903.34elo | CI 889.05–917.64 | 24 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 903.3444757105251 \| elo \| rlb_1MFkk9yZHssERh \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkk9yZHssERh participantId par_1MFltlQRYSJKls sourceModelVersion minimax-m3 weighted false ### Reported statistics Uncertainty Confidence interval: 889.05–917.64 confidenceIntervalLowerOffset 14.290585944588543 confidenceIntervalUpperOffset 14.290585944588543 totalMatches 13453 wins 6885 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) Source rapidata Original model label minimax-m3 Source version v1 Observed 2026-10-21T16:37:40.342Z Evidence SHA-256 `2f5c8d08728735790b500d930d71b66f04253f1209f7c1c3da0db0846c163fcf` Source locator `/items/44` | | | | | | | | | [SAGE / automata](https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata.md) | 37.3% | SE ±6.22 pp | 17 / 41 | $0.02 | 115.09source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.302 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.020054 \| USD \| per_test \| Lower is better \| \| `latency` \| 115.085 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.22 pp sourcePopulation 91 stderr 6.222 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__trusts_estates_private_client.md) | 85.5% | SE ±2.18 pp | 26 / 49 | $2.47 | 1,796.99source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.496 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.467191 \| USD \| per_test \| Lower is better \| \| `latency` \| 1796.99 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.18 pp sourcePopulation 81 stderr 2.18 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__trusts_estates_private_client/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate arbitration international dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__arbitration_international_dispute_resolution.md) | 86.74% | SE ±2.03 pp | 21 / 49 | $2.3 | 1,866.31source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.738 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.296246 \| USD \| per_test \| Lower is better \| \| `latency` \| 1866.306 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.03 pp sourcePopulation 81 stderr 2.034 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / tax](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atax.md) | 0% | SE ±0 pp | 3 / 49 | $1.55 | 1,470.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.553621 \| USD \| per_test \| Lower is better \| \| `latency` \| 1470.598 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/tax/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__corporate_governance.md) | 88.01% | SE ±1.9 pp | 19 / 49 | $1.37 | 1,402.6source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.014 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.37422 \| USD \| per_test \| Lower is better \| \| `latency` \| 1402.604 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 81 stderr 1.904 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__corporate_governance/minimax~1MiniMax-M3` | | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 90.45% | — | 55 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.45 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.96 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.57 \| percent \| category \| Higher is better \| \| `language` \| 94.71 \| percent \| category \| Higher is better \| \| `utility` \| 93.59 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.27 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.51 \| percent \| category \| Higher is better \| \| `rule_following` \| 69.18 \| percent \| category \| Higher is better \| \| `hallucination` \| 97.83 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration MiniMax M3 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label MiniMax M3 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/67` | | | | | | | | | [Code Migration / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acode_quality.md) | 3.72% | SE ±0.08 pp | 27 / 47 | $7.07 | 4,428.26source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.718 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.072659 \| USD \| per_test \| Lower is better \| \| `latency` \| 4428.262 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.08 pp sourcePopulation 79 stderr 0.083 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/code_quality/minimax~1MiniMax-M3` | | | | | | | | | [EMB / misc](https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc.md) | 50.02% | SE ±5.09 pp | 35 / 47 | $2.18 | 2,177.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.022 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.184482 \| USD \| per_test \| Lower is better \| \| `latency` \| 2177.177 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.09 pp sourcePopulation 76 stderr 5.091 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/misc/minimax~1MiniMax-M3` | | | | | | | | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,161elo | — | 33 / 65 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1161 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion minimax-m3 variationName public ### Reported statistics averageGenerationTimeMs 72285 battles 506 losses 271 standardError Not reported winRate 46.4 wins 235 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label MiniMax M3 Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/47` | | | | | | | | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,456.27 | — | 61 / 132 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.2749384935378 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1442.2504125172827 rank 99 upper 1470.2994644697928 variance 51.201207155752975 votes 2399 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2936/row` | | | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,445.66 | — | 50 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.6567692439367 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1440.64832193453 rank 69 upper 1450.6652165533435 variance 6.529952713789778 votes 29633 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8586/row` | | | | | | | | | [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,259.43 | — | 53 / 73 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1259.4264558182072 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control ### Reported statistics lower 1246.7326767772752 rank 67 upper 1272.120234859139 variance 41.94553003457342 votes 2405 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/874/row` | | | | | | | | | [Terminal-Bench 4.0 / hardware](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Ahardware.md) | 0% | SE ±0 pp | 21 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 52 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/hardware/minimax~1MiniMax-M3` | | | | | | | | | [SWE-bench Multimodal / fusion next](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Afusion_next.md) | 33.33% | SE ±7.97 pp | 11 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.97 pp sourcePopulation 20 stderr 7.968 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/fusion_next/minimax~1MiniMax-M3` | | | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,447.26 | — | 54 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.256114176686 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1442.8373702747358 rank 82 upper 1451.6748580786361 variance 5.082781980074831 votes 43582 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3532/row` | | | | | | | | | [ProofBench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aproof_bench%3Aoverall.md) | 18% | SE ±3.86 pp | 30 / 34 | $0.42 | 718.66source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_proof_bench.i3Hwh8rW.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 18 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.419224 \| USD \| per_test \| Lower is better \| \| `latency` \| 718.66 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.86 pp sourcePopulation 52 stderr 3.861 tokenTotals {"cache_read_tokens":151053885,"cache_write_tokens":0,"input_tokens":162739395,"output_tokens":4876274,"reasoning_tokens":1498488} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_proof_bench.i3Hwh8rW.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.1 Observed 2026-10-21T16:46:01.401Z Evidence SHA-256 `22be2aca25de5c4a9eb6448a95713e09a7c97126dfc6f4f75c4afd0e563209cb` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Vals Multimodal Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aoverall.md) | 59.97% | SE ±1.65 pp | 15 / 20 | $1.08 | 1,076.24source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.974 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.076447 \| USD \| per_test \| Lower is better \| \| `latency` \| 1076.237 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.65 pp sourcePopulation 33 stderr 1.646 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [SWE-bench Multimodal / highlight js](https://benchize.com/benchmarks/vals-ai%3Aswebench-multimodal%3Ahighlight_js.md) | 33.33% | SE ±7.65 pp | 11 / 14 | — | — | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.333 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.65 pp sourcePopulation 20 stderr 7.647 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench_multimodal.C7UOLrm7.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:12.211Z Evidence SHA-256 `5302c42065b017d7deaa43d9e34be1ec69893b7ec4cceb6c07bfbabbd20b1f82` Source locator `/tasks/highlight_js/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ahealthcare_life_sciences.md) | 20% | SE ±20 pp | 5 / 49 | $1.46 | 1,436.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.4604 \| USD \| per_test \| Lower is better \| \| `latency` \| 1436.112 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/healthcare_life_sciences/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent (v2) / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_quantitative_analysis.md) | 66.48% | SE ±0.82 pp | 36 / 50 | $0.31 | 376.51source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.483 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.308361 \| USD \| per_test \| Lower is better \| \| `latency` \| 376.513 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.82 pp sourcePopulation 80 stderr 0.823 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_quantitative_analysis/minimax~1MiniMax-M3` | | | | | | | | | [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,149.7elo | CI 1,135.7–1,161.9 | 20 / 26 | — | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1149.7 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,135.7–1,161.9 confidenceIntervalHigh 1161.9 confidenceIntervalLow 1135.7 scenarios 119 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label minimax-m3 Source version eqbench4 Observed 2026-10-21T16:35:00.261Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/19` | | | | | | | | | [LiveBench](https://benchize.com/benchmarks/livebench%3Atasks.md) | 75% | — | 9 / 10 | — | — | [LiveBench](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 75 \| percent \| reported \| Higher is better \| \| `code_completion` \| 67.391 \| percent \| reported \| Higher is better \| \| `code_generation` \| 69.014 \| percent \| reported \| Higher is better \| \| `connections` \| 96.333 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 84.614 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 56 \| percent \| reported \| Higher is better \| \| `javascript` \| 63.636 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 66 \| percent \| reported \| Higher is better \| \| `math_comp` \| 91.176 \| percent \| reported \| Higher is better \| \| `olympiad` \| 85.614 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 55.933 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 50.174 \| percent \| reported \| Higher is better \| \| `python` \| 35 \| percent \| reported \| Higher is better \| \| `simplify` \| 56.617 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 63.55 \| percent \| reported \| Higher is better \| \| `summarize` \| 53.933 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 45.846 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 98.039 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 76.923 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 84 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 61 \| percent \| reported \| Higher is better \| ### Configuration Model configuration minimax-m3 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label minimax-m3 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/24` | | | | | | | | | [Finance Agent (v2) / disclosure analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Adisclosure_analysis.md) | 59.83% | SE ±1.98 pp | 32 / 50 | $0.35 | 471.87source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.831 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.346007 \| USD \| per_test \| Lower is better \| \| `latency` \| 471.873 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.98 pp sourcePopulation 80 stderr 1.976 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/disclosure_analysis/minimax~1MiniMax-M3` | | | | | | | | | [Terminal-Bench 2.1 / easy](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aeasy.md) | 83.33% | SE ±8.33 pp | 25 / 43 | $4.58 | 22,771source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.333 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.582903 \| USD \| per_test \| Lower is better \| \| `latency` \| 22771.001 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.33 pp sourcePopulation 76 stderr 8.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/easy/minimax~1MiniMax-M3` | | | | | | | | | [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 71.11% | SE ±6.83 pp | 69 / 123 | — | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7111111111111111 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7111111111111111 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion MiniMax-M3 ### Reported statistics Uncertainty Standard error: ±6.83 pp standardError 0.0683294324254051 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label MiniMax-M3 Source version OTIS Mock AIME 2024-2025 Evaluated 2026-08-10T17:46:09.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5b411612f91e155dff4b09d09b548b42f7936482ea8b3c00b510bd46e2f6bc2c` Source locator `/rows/73` | | | | | | | | | [SkillsBench / with skills](https://benchize.com/benchmarks/vals-ai%3Askillsbench%3Awith_skills.md) | 51.5% | SE ±4.5 pp | 15 / 20 | $0.5 | 927.98source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.497 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.504553 \| USD \| per_test \| Lower is better \| \| `latency` \| 927.977 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.5 pp sourcePopulation 35 stderr 4.498 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:11.147Z Evidence SHA-256 `aaad242949d81b7c7c61c36d4895d4460e9146760c1e6b4b38d235a16043bc61` Source locator `/tasks/with_skills/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent (v2) / market analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Amarket_analysis.md) | 59.01% | SE ±0.33 pp | 31 / 50 | $0.19 | 369.2source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.007 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.194569 \| USD \| per_test \| Lower is better \| \| `latency` \| 369.203 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.33 pp sourcePopulation 80 stderr 0.331 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/market_analysis/minimax~1MiniMax-M3` | | | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,404.28 | — | 51 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.2802015069622 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1397.8008550111679 rank 86 upper 1410.7595480027567 variance 10.928642729789146 votes 12117 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1307/row` | | | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,442.8 | — | 65 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1442.8016624930078 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1433.8439652345323 rank 106 upper 1451.7593597514833 variance 20.887986548818123 votes 5344 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5213/row` | | | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,440.68 | — | 55 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1440.6794317392246 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1431.0967796904392 rank 95 upper 1450.2620837880095 variance 23.904257360097272 votes 4432 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6407/row` | | | | | | | | | [SWE-bench / overall](https://benchize.com/benchmarks/vals-ai%3Aswebench%3Aoverall.md) | 75% | SE ±1.94 pp | 22 / 39 | $0.42 | 726.04source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.416355 \| USD \| per_test \| Lower is better \| \| `latency` \| 726.041 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 88 stderr 1.938 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/overall/minimax~1MiniMax-M3` | | | | | | | | | [Finance Agent (v2) / earnings analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aearnings_analysis.md) | 66.19% | SE ±1.41 pp | 35 / 50 | $0.13 | 303.41source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.191 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.130797 \| USD \| per_test \| Lower is better \| \| `latency` \| 303.41 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.41 pp sourcePopulation 80 stderr 1.409 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/earnings_analysis/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__litigation_dispute_resolution.md) | 88.76% | SE ±1.94 pp | 12 / 49 | $1.54 | 1,402.92source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.764 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.540985 \| USD \| per_test \| Lower is better \| \| `latency` \| 1402.92 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.94 pp sourcePopulation 81 stderr 1.936 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__litigation_dispute_resolution/minimax~1MiniMax-M3` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Abankruptcy_restructuring.md) | 0% | SE ±0 pp | 3 / 49 | $1.51 | 1,343.5source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.508844 \| USD \| per_test \| Lower is better \| \| `latency` \| 1343.498 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/bankruptcy_restructuring/minimax~1MiniMax-M3` | | | | | | | | | [MMLU Pro / biology](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Abiology.md) | 92.75% | SE ±1.01 pp | 24 / 40 | $0.00285 | 33.2source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.748 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002851 \| USD \| per_test \| Lower is better \| \| `latency` \| 33.196 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.01 pp sourcePopulation 138 stderr 1.01 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/biology/minimax~1MiniMax-M3` | | | | | | | | [Next page](https://benchize.com/models/minimax-m3.md?cursor=53398418dc1d60c320e0a3c60131ece59341c04be31f8747f63e41e9e4bd3a84) --- Cite as: MiniMax M3 — Benchize, https://benchize.com/models/minimax-m3 (retrieved 2026-10-21)