# Qwen3 30B A3B Instruct 2507

> Source: Benchize (https://benchize.com) — https://benchize.com/models/qwen3-30b-a3b-instruct-2507. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/qwen3-30b-a3b-instruct-2507.

Alibaba

Canonical URL: https://benchize.com/models/qwen3-30b-a3b-instruct-2507
Last updated: Thu, 22 Oct 2026 05:40:11 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Alibaba

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,432.7 | — | 90 / 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` \| 1432.697636894723 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1418.2109495708057 rank 155 upper 1447.1843242186403 variance 54.631357361010885 votes 1753 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/571/row` |  |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,437.35 | — | 98 / 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` \| 1437.3538711518386 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1428.5063587444936 rank 171 upper 1446.2013835591836 variance 20.377278386126108 votes 4615 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/980/row` |  |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,380.98 | — | 102 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1380.976467584582 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1372.4114712077435 rank 191 upper 1389.5414639614205 variance 19.096693823728394 votes 4942 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8708/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,341.37 | — | 111 / 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` \| 1341.3712442255583 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1332.839071870062 rank 206 upper 1349.9034165810544 variance 18.95060405482622 votes 5073 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7323/row` |  |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,329.57 | — | 83 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1329.569276042171 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1304.7764940690522 rank 150 upper 1354.36205801529 variance 160.01265838261338 votes 595 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8383/row` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,416.52 | — | 102 / 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` \| 1416.5198057933471 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1407.7776425462243 rank 184 upper 1425.26196904047 variance 19.894894571728056 votes 4747 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4051/row` |  |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,371.62 | — | 97 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1371.6161047615697 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1365.763792735969 rank 171 upper 1377.46841678717 variance 8.91576810884571 votes 13552 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9901/row` |  |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,415.88 | — | 91 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.8818904637694 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1407.0786688075502 rank 153 upper 1424.6851121199886 variance 20.17377125352681 votes 4615 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/962/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,406.5 | — | 94 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1406.4998661473805 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1397.7934808288796 rank 164 upper 1415.206251465881 variance 19.732385234968422 votes 4747 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4031/row` |  |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,371.46 | — | 100 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1371.4615381159942 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1357.1077001767626 rank 187 upper 1385.8153760552261 variance 53.63396386701333 votes 1563 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10570/row` |  |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,398.05 | — | 88 / 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` \| 1398.0549233369343 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1375.4386885200495 rank 155 upper 1420.6711581538193 variance 133.15099840118828 votes 716 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10919/row` |  |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,370.47 | — | 88 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.4662245623244 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1344.464560402549 rank 163 upper 1396.4678887221 variance 175.99734127973525 votes 524 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3299/row` |  |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,336.04 | — | 107 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1336.0397153634324 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1327.5801092982176 rank 198 upper 1344.4993214286474 variance 18.629624348202345 votes 5073 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7315/row` |  |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 55.62% | SE ±2.88 pp | 101 / 126 | — | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5561868686868687 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.5561868686868687 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen3-30b-a3b-instruct-2507 ### Reported statistics Uncertainty Standard error: ±2.88 pp standardError 0.028844434239616544 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label qwen3-30b-a3b-instruct-2507 Source version GPQA diamond Evaluated 2026-08-30T22:44:04.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `9ef0b938bdd8406b029d595983ee8ad3a80bd9d64b82605b91b5ce39ba650c39` Source locator `/rows/18` |  |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,389.21 | — | 91 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1389.2059997223703 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1379.84827762529 rank 157 upper 1398.5637218194506 variance 22.79523663626369 votes 4116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4439/row` |  |  |  |  |  |  |  |
| [Berkeley Function Calling Leaderboard](https://benchize.com/benchmarks/bfcl%3Aoverall.md) | 41.39% | — | 11 / 26 | $5.62 | 5.95s | [Berkeley Function Calling Leaderboard](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.39 \| percent \| reported \| Higher is better \| \| `cost_total` \| 5.62 \| USD \| evaluation_total \| Lower is better \| \| `latency_mean` \| 5.95 \| seconds \| per_call_mean \| Lower is better \| \| `latency_sd` \| 25.48 \| seconds \| per_call_sd \| Lower is better \| \| `non_live_ast_acc` \| 85.77 \| percent \| reported_task_score \| Higher is better \| \| `non_live_simple_ast` \| 68.58 \| percent \| reported_task_score \| Higher is better \| \| `non_live_multiple_ast` \| 94.5 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_ast` \| 91.5 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_multiple_ast` \| 88.5 \| percent \| reported_task_score \| Higher is better \| \| `live_acc` \| 77.94 \| percent \| reported_task_score \| Higher is better \| \| `live_simple_ast` \| 83.33 \| percent \| reported_task_score \| Higher is better \| \| `live_multiple_ast` \| 76.83 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_ast` \| 68.75 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_multiple_ast` \| 75 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_acc` \| 30 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_base` \| 43.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_func` \| 10.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_param` \| 25 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_long_context` \| 41 \| percent \| reported_task_score \| Higher is better \| \| `web_search_acc` \| 22.5 \| percent \| reported_task_score \| Higher is better \| \| `web_search_base` \| 21 \| percent \| reported_task_score \| Higher is better \| \| `web_search_no_snippet` \| 24 \| percent \| reported_task_score \| Higher is better \| \| `memory_acc` \| 17.63 \| percent \| reported_task_score \| Higher is better \| \| `memory_kv` \| 9.03 \| percent \| reported_task_score \| Higher is better \| \| `memory_vector` \| 9.03 \| percent \| reported_task_score \| Higher is better \| \| `memory_recursive_summarization` \| 34.84 \| percent \| reported_task_score \| Higher is better \| \| `relevance_detection` \| 81.25 \| percent \| reported_task_score \| Higher is better \| \| `irrelevance_detection` \| 79.9 \| percent \| reported_task_score \| Higher is better \| \| `latency_p95` \| 12.7 \| seconds \| per_call_p95 \| Lower is better \| ### Configuration mode FC sourceRelease 2025-12-16 ### Reported statistics rank 41 ### Source [Original source](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) Source Berkeley Function Calling Leaderboard Original model label Qwen3-30B-A3B-Instruct-2507 Observed 2026-10-22T02:40:09.731Z Evidence SHA-256 `ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6` Source locator `/rows/41` |  |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,334.45 | — | 102 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1334.453286423153 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1325.318622068555 rank 185 upper 1343.587950777751 variance 21.721459676114666 votes 4122 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4877/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,384.08 | — | 103 / 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` \| 1384.0849943472856 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1368.667566757119 rank 192 upper 1399.5024219374523 variance 61.8767724952684 votes 1463 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5299/row` |  |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,379.32 | — | 101 / 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` \| 1379.3247721538955 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1369.728322629555 rank 189 upper 1388.9212216782362 variance 23.97314347797139 votes 3929 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9504/row` |  |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,313.89 | — | 96 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1313.8932534112278 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1288.6415085553708 rank 177 upper 1339.1449982670847 variance 165.9917880234045 votes 595 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8410/row` |  |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,382.34 | — | 103 / 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` \| 1382.3422413846652 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1377.4363606649 rank 189 upper 1387.2481221044306 variance 6.265241086774446 votes 23315 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/188/row` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,406.94 | — | 102 / 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` \| 1406.939958826898 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1400.6382413217852 rank 182 upper 1413.2416763320107 variance 10.337646547274305 votes 10974 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3632/row` |  |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,396.15 | — | 104 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.1492882219306 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1379.3212918412917 rank 187 upper 1412.9772846025699 variance 73.7171672025455 votes 1174 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2657/row` |  |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,378.41 | — | 100 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.4096804431047 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1368.8689934588624 rank 177 upper 1387.9503674273467 variance 23.69534918373534 votes 3929 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9492/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,428.18 | — | 99 / 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` \| 1428.1774117038726 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1421.0575970320563 rank 173 upper 1435.297226375689 variance 13.19596625321925 votes 7960 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6873/row` |  |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,383.81 | — | 98 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1383.814937982436 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1378.9352107479194 rank 171 upper 1388.6946652169527 variance 6.198618544342796 votes 23315 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/170/row` |  |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,386.64 | — | 99 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1386.6374290628203 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1371.261622009161 rank 171 upper 1402.0132361164794 variance 61.543141183181994 votes 1463 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5278/row` |  |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,367.72 | — | 101 / 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` \| 1367.716242011344 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1361.8300407924837 rank 184 upper 1373.6024432302045 variance 9.019324794598175 votes 13552 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9914/row` |  |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,344.2 | — | 97 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1344.2022107950381 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1328.8725512833082 rank 182 upper 1359.5318703067678 variance 61.174275637062614 votes 1541 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10329/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,397.79 | — | 97 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1397.7898717639364 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1391.5170521632504 rank 168 upper 1404.062691364622 variance 10.243052855539258 votes 10974 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3618/row` |  |  |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 62.22% | SE ±6.51 pp | 83 / 124 | — | — | [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` \| 0.6222222222222222 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.6222222222222222 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen3-30b-a3b-instruct-2507 ### Reported statistics Uncertainty Standard error: ±6.51 pp standardError 0.06509619058885623 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label qwen3-30b-a3b-instruct-2507 Source version OTIS Mock AIME 2024-2025 Evaluated 2026-08-30T22:44:11.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/25` |  |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,379.43 | — | 80 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1379.4263642593328 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1353.7172940705 rank 143 upper 1405.1354344481651 variance 172.05866854896826 votes 524 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3279/row` |  |  |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 34.58% | — | 38 / 39 | — | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 34.58 \| percent \| overall \| Higher is better \| \| `stability` \| 0.153 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.343 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.548 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion qwen/qwen3-30b-a3b-instruct-2507 ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label qwen/qwen3-30b-a3b-instruct-2507 Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/15` |  |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,337.48 | — | 75 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1337.4846948444078 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1315.3828533039966 rank 137 upper 1359.5865363848193 variance 127.16299257092703 votes 766 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8087/row` |  |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,411.48 | — | 90 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1411.4782038948197 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1395.0286714869658 rank 149 upper 1427.9277363026733 variance 70.43863518186564 votes 1208 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6061/row` |  |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,419.23 | — | 79 / 132 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.2298236443949 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1387.2291667615198 rank 131 upper 1451.2304805272697 variance 266.5763421486996 votes 336 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2968/row` |  |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,392.9 | — | 95 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1392.8983977847668 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1383.1106578663457 rank 171 upper 1402.6861377031873 variance 24.938404179831107 votes 3677 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5668/row` |  |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,392.32 | — | 94 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1392.3181845338445 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1375.9596605444149 rank 166 upper 1408.676708523274 variance 69.66137595206308 votes 1327 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6478/row` |  |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,418.14 | — | 86 / 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` \| 1418.1355304137924 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1386.1085809272795 rank 153 upper 1450.1624799003057 variance 267.0145747459353 votes 336 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2990/row` |  |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,358.08 | — | 103 / 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` \| 1358.0777431464705 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1351.290303340959 rank 188 upper 1364.8651829519818 variance 11.992667698339526 votes 16354 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2241/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,400.22 | — | 100 / 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` \| 1400.2238741395956 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1383.789527533425 rank 185 upper 1416.6582207457666 variance 70.3086407998924 votes 1327 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6497/row` |  |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,378.25 | — | 98 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.2461308833049 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1369.7234102725165 rank 174 upper 1386.7688514940933 variance 18.90864122199058 votes 4942 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8691/row` |  |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,396.7 | — | 95 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.6992126128944 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1380.0380959724532 rank 163 upper 1413.3603292533355 variance 72.26234112181004 votes 1174 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2633/row` |  |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,325.18 | — | 80 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.177447415444 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1302.8458057868143 rank 153 upper 1347.5090890440738 variance 129.82105005083508 votes 766 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8103/row` |  |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,369.48 | — | 98 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.4764728919818 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1355.1889161028498 rank 175 upper 1383.7640296811137 variance 53.13978062266063 votes 1563 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10558/row` |  |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,394.33 | — | 100 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1394.3295428251968 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1379.205061709577 rank 172 upper 1409.4540239408163 variance 59.547671781473014 votes 1394 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9084/row` |  |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,392.87 | — | 103 / 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` \| 1392.8655421560832 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1386.2849465640782 rank 189 upper 1399.4461377480882 variance 11.272862828109645 votes 9755 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1825/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_entertainment_and_sports_and_media.md) | 1,330.9 | — | 104 / 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` \| 1330.8968185446815 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1321.6729761292652 rank 198 upper 1340.120660960098 variance 22.147645692857115 votes 4122 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4890/row` |  |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,357.88 | — | 98 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1357.8797392798956 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1351.19480864789 rank 171 upper 1364.564669911901 variance 11.633158037250526 votes 16354 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2224/row` |  |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,403.96 | — | 81 / 134 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.9555302434987 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1381.6086099532868 rank 141 upper 1426.3024505337107 variance 129.99875041400335 votes 716 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10905/row` |  |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,416.71 | — | 92 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1416.7146569020879 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1409.6243917781317 rank 156 upper 1423.804922026044 variance 13.086658447871901 votes 7960 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6856/row` |  |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,432.47 | — | 87 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.4712104954249 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1418.1012439335977 rank 147 upper 1446.8411770572518 variance 53.754562687390035 votes 1753 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/563/row` |  |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,317.14 | — | 108 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1317.1412362311235 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1306.221848275755 rank 205 upper 1328.0606241864919 variance 31.03847753815001 votes 2965 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1426/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,398.51 | — | 101 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1398.5073421302309 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1381.9432824143519 rank 175 upper 1415.07140184611 variance 71.42288569987257 votes 1208 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6087/row` |  |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,318.58 | — | 114 / 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` \| 1318.5828893848848 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1307.5757772343004 rank 215 upper 1329.590001535469 variance 31.53919475665438 votes 2965 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1436/row` |  |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,293 | — | 128 / 191 | — | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1293 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen3_30b_a3b_instruct_2507 ### Reported statistics coverageCount 27 draws 0 judged 49 losses 29 rank 202 ratingDeviation 28 wins 20 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen3 30B A3B Instruct 2507 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/192` |  |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,391.2 | — | 99 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.201103938995 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1384.657597861042 rank 174 upper 1397.7446100169482 variance 11.146148843649838 votes 9755 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1810/row` |  |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,363.03 | — | 97 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1363.0288264795504 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1355.196483290783 rank 176 upper 1370.8611696683176 variance 15.96934984599039 votes 5970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7709/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,395.03 | — | 103 / 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` \| 1395.0304926050842 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1385.180419604187 rank 190 upper 1404.8805656059812 variance 25.257055366656978 votes 3677 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5687/row` |  |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,365.85 | — | 104 / 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` \| 1365.8505625630091 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1357.987978017058 rank 193 upper 1373.7131471089604 variance 16.092906009874063 votes 5970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7726/row` |  |  |  |  |  |  |  |
| [Berkeley Function Calling Leaderboard](https://benchize.com/benchmarks/bfcl%3Aoverall.md) | 36.7% | — | 16 / 26 | $1.56 | 1.24s | [Berkeley Function Calling Leaderboard](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.7 \| percent \| reported \| Higher is better \| \| `cost_total` \| 1.56 \| USD \| evaluation_total \| Lower is better \| \| `latency_mean` \| 1.24 \| seconds \| per_call_mean \| Lower is better \| \| `latency_sd` \| 7.9 \| seconds \| per_call_sd \| Lower is better \| \| `non_live_ast_acc` \| 88.92 \| percent \| reported_task_score \| Higher is better \| \| `non_live_simple_ast` \| 80.67 \| percent \| reported_task_score \| Higher is better \| \| `non_live_multiple_ast` \| 93 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_ast` \| 94 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_multiple_ast` \| 88 \| percent \| reported_task_score \| Higher is better \| \| `live_acc` \| 78.39 \| percent \| reported_task_score \| Higher is better \| \| `live_simple_ast` \| 82.56 \| percent \| reported_task_score \| Higher is better \| \| `live_multiple_ast` \| 77.49 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_ast` \| 87.5 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_multiple_ast` \| 66.67 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_acc` \| 23.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_base` \| 33 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_func` \| 16 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_param` \| 16 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_long_context` \| 29 \| percent \| reported_task_score \| Higher is better \| \| `web_search_acc` \| 17.5 \| percent \| reported_task_score \| Higher is better \| \| `web_search_base` \| 15 \| percent \| reported_task_score \| Higher is better \| \| `web_search_no_snippet` \| 20 \| percent \| reported_task_score \| Higher is better \| \| `memory_acc` \| 9.68 \| percent \| reported_task_score \| Higher is better \| \| `memory_kv` \| 5.81 \| percent \| reported_task_score \| Higher is better \| \| `memory_vector` \| 6.45 \| percent \| reported_task_score \| Higher is better \| \| `memory_recursive_summarization` \| 16.77 \| percent \| reported_task_score \| Higher is better \| \| `relevance_detection` \| 93.75 \| percent \| reported_task_score \| Higher is better \| \| `irrelevance_detection` \| 74.85 \| percent \| reported_task_score \| Higher is better \| \| `latency_p95` \| 2.84 \| seconds \| per_call_p95 \| Lower is better \| ### Configuration mode Prompt sourceRelease 2025-12-16 ### Reported statistics rank 53 ### Source [Original source](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) Source Berkeley Function Calling Leaderboard Original model label Qwen3-30B-A3B-Instruct-2507 Observed 2026-10-22T02:40:09.731Z Evidence SHA-256 `ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6` Source locator `/rows/53` |  |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,377.84 | — | 108 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1377.8449229147998 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1362.622683539787 rank 191 upper 1393.0671622898126 variance 60.31994156540765 votes 1394 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9103/row` |  |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,353.16 | — | 91 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1353.1576214231718 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1337.953622872509 rank 165 upper 1368.3616199738346 variance 60.1754652902383 votes 1541 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10312/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,397.98 | — | 94 / 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` \| 1397.9786610714034 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1388.5894677588458 rank 168 upper 1407.367854383961 variance 22.948821053520444 votes 4116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4450/row` |  |  |  |  |  |  |  |

---
Cite as: Qwen3 30B A3B Instruct 2507 — Benchize, https://benchize.com/models/qwen3-30b-a3b-instruct-2507 (retrieved 2026-10-22)