# GPT-5.2High

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-2-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-2-high.

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-2-high
Last updated: Wed, 21 Oct 2026 18:05:10 GMT

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

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,426.84 | — | 69 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.8386568586193 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1416.9106500741889 rank 118 upper 1436.7666636430497 variance 25.65830412673476 votes 3768 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5225/row` |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,391.64 | — | 76 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.6432913085575 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1385.4988851736373 rank 127 upper 1397.7876974434778 variance 9.827966018395239 votes 11509 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7244/row` |  |  |  |  |  |  |
| [AIME 2025](https://benchize.com/benchmarks/aime-2025.md) | 100% | 95% CI 100–100% | 1 / 35 | 0.11usd per problem | [matharena · aime--aime_2025](https://matharena.ai/competition_tables/aime--aime_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.11 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 100–100% confidenceInterval95 0.00 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2025) Source matharena Original model label GPT-5.2 (high) Source version aime--aime_2025 Observed 2026-10-21T16:52:35.082Z Evidence SHA-256 `fab0abcecc4032852ef2cbd2a84d34ffc42202be358b2994bfaba44ae7a0cd9a` Source locator `/table/rows/0` |  |  |  |  |  |  |
| [Kangaroo 2025 9-10](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_9-10.md) | 100% | 95% CI 100–100% | 1 / 15 | 0.03usd per problem | [matharena · kangaroo--kangaroo_2025_9-10](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.025 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_9-10 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 100–100% confidenceInterval95 0.00 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_9-10 Observed 2026-10-21T16:52:33.536Z Evidence SHA-256 `52964b89ab1a06cf2e79ec946b33004aa40ca31f1ec26888e6dd0f0a7994223a` Source locator `/table/rows/1` |  |  |  |  |  |  |
| [Arena vision / homework (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahomework--config-vision.md) | 1,276.24 | — | 48 / 73 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1276.2416679020682 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1264.686200373072 rank 59 upper 1287.7971354310644 variance 34.759927425059345 votes 2888 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/866/row` |  |  |  |  |  |  |
| [Arena vision style control / ocr](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr.md) | 1,260.05 | — | 47 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1260.051886535324 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1253.6372611193326 rank 60 upper 1266.4665119513154 variance 10.711404481500585 votes 12905 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1078/row` |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,447.43 | — | 61 / 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` \| 1447.4266627331608 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1437.3692769084396 rank 99 upper 1457.484048557882 variance 26.331405424001005 votes 3768 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5206/row` |  |  |  |  |  |  |
| [SMT 2025](https://benchize.com/benchmarks/matharena%3Asmt--smt_2025.md) | 91.98% | 95% CI 88.32–95.64% | 3 / 25 | 0.13usd per problem | [matharena · smt--smt_2025](https://matharena.ai/competition_tables/smt--smt_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.98 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.13 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition smt--smt_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 88.32–95.64% confidenceInterval95 3.66 problems 53 ### Source [Original source](https://matharena.ai/competition_tables/smt--smt_2025) Source matharena Original model label GPT-5.2 (high) Source version smt--smt_2025 Observed 2026-10-21T16:52:36.547Z Evidence SHA-256 `1b4f6f8bafc1688e4557a024513f68befa31aff48fd0623fb4892a61263433b0` Source locator `/table/rows/4` |  |  |  |  |  |  |
| [τ-bench retail](https://benchize.com/benchmarks/sierra%3Aretail.md) | 81.58% | — | 2 / 8 | $0.07 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2_sierra_2026-02-26/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 81.58 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 69.59 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 59.87 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 51.75 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.07156 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-05","notes":"Evaluated using AllTools retrieval (BM25 + dense OpenAI text-embedding-3-large + sandboxed shell). User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking_knowledge domain only — other domains intentionally excluded from this comparison; the AllTools setting standardizes retrieval across models. banking_knowledge re-graded under tau2-bench v1.0.1 grading fixes on 2026-07-15 (extra-read logging #329, numeric-argument normalization #397, T077-T086 gold trajectories #402); scores prior to v1.0.1 are not comparable.","tau2_bench_version":"1.0.1","user_simulator":"gpt-5.2","verification":{"details":"Verified evaluation with full trajectory data available. Standard tau-bench scaffold.","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort high retrieval Not reported sourceSubmission gpt-5-2_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.424Z Evidence SHA-256 `343687b822edbcbff42a4d4632ecc6288a58d9817a7a02c8533081c5709c0ac6` Source locator `/results/retail` |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,479.8 | — | 41 / 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` \| 1479.802566233453 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1462.7825678599775 rank 63 upper 1496.822564606929 variance 75.40894179903658 votes 1439 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2900/row` |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,404.74 | — | 71 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.740710913681 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1400.3727231385421 rank 119 upper 1409.1086986888197 variance 4.966685338648109 votes 28429 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9849/row` |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,402.96 | — | 77 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1402.9629173386304 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1398.2626722416746 rank 129 upper 1407.663162435586 variance 5.751019339955652 votes 36903 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2182/row` |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,420.54 | — | 79 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.5360542355088 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1410.0966171117157 rank 130 upper 1430.9754913593015 variance 28.369911679005412 votes 3506 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6442/row` |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,459.67 | — | 63 / 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` \| 1459.6741454349278 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1455.2569581016812 rank 101 upper 1464.0913327681744 variance 5.07920163868062 votes 29881 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3551/row` |  |  |  |  |  |  |
| [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 28% | — | 117 / 191 | — | [bullshitbench · v2](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `green_rate` \| 0.28 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.22 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.0 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.02 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort high suite v2 thinkingEnabled true ### Reported statistics acceptedCount 22 answeredCount 100 clearCount 28 errorCount 0 partialCount 50 rank 117 refusalCount 0 sampleSize 100 ### Source [Original source](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=3c655234d15967738f95da696e3f938d4862dcf7) Source bullshitbench Original model label openai/gpt-5.2 Source version v2 Observed 2026-10-21T16:33:56.675Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/116` |  |  |  |  |  |  |
| [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 98.33% | 95% CI 96.04–100.62% | 4 / 21 | 0.12usd per problem | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.12 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 96.04–100.62% confidenceInterval95 2.29 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label GPT-5.2 (high) Source version aime--aime_2026 Observed 2026-10-21T16:52:37.816Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/3` |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,411.6 | — | 69 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1411.6021598129494 \| rating \| reported \| Higher is better \| ### Configuration category russian config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1403.8433624339464 rank 116 upper 1419.3609571919526 variance 15.670853073871555 votes 6311 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10499/row` |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,369.87 | — | 60 / 124 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.8691532230346 \| rating \| reported \| Higher is better \| ### Configuration category korean config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1348.0683327748955 rank 110 upper 1391.6699736711737 variance 123.72272993053197 votes 786 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8343/row` |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,408.48 | — | 79 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.4760775103475 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1403.0460228809459 rank 134 upper 1413.9061321397494 variance 7.675597905526808 votes 17221 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8651/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) | 1,388.03 | — | 76 / 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` \| 1388.0263149627142 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1381.2609565412677 rank 133 upper 1394.791673384161 variance 11.914763819430338 votes 9343 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4825/row` |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--visual_math.md) | 86.53% | 95% CI 83.97–89.09% | 6 / 15 | 0.06usd per problem | [matharena · overall--visual_math](https://matharena.ai/competition_tables/overall--visual_math) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.53 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.059 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--visual_math predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 83.97–89.09% confidenceInterval95 2.56 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--visual_math) Source matharena Original model label GPT-5.2 (high) Source version overall--visual_math Observed 2026-10-21T16:52:30.998Z Evidence SHA-256 `b38d1f465012aab8b7d0930aea897d4e5be10ec02c16643c24c9251c8febb173` Source locator `/table/rows/6` |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,446.55 | — | 78 / 146 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.5523107433846 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1436.3774993583718 rank 133 upper 1456.7271221283975 variance 26.949862422807186 votes 3579 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/549/row` |  |  |  |  |  |  |
| [Arena vision / english (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aenglish--config-vision.md) | 1,243.19 | — | 54 / 82 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1243.187462671484 \| rating \| reported \| Higher is better \| ### Configuration category english config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1234.466041673289 rank 72 upper 1251.9088836696783 variance 19.800598621021916 votes 7347 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/661/row` |  |  |  |  |  |  |
| [Project Euler](https://benchize.com/benchmarks/matharena%3Aeuler--euler.md) | 81.59% | — | 5 / 10 | 1.88usd per problem | [matharena · euler--euler](https://matharena.ai/competition_tables/euler--euler) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.59 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.88 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition euler--euler predicted true Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics confidenceInterval95 Not reported problems 50 ### Source [Original source](https://matharena.ai/competition_tables/euler--euler) Source matharena Original model label GPT-5.2 (high) Source version euler--euler Observed 2026-10-21T16:52:41.889Z Evidence SHA-256 `f965e69ef39c2cc9c950899809f028eda1d49070afaf6272153ba51fa222ba3d` Source locator `/table/rows/4` |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,419.69 | — | 39 / 120 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.6934315281796 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1390.2056208191138 rank 52 upper 1449.1812422372452 variance 226.35436718193662 votes 446 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8002/row` |  |  |  |  |  |  |
| [Arena vision / captioning (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acaptioning--config-vision.md) | 1,266.64 | — | 8 / 22 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1266.6369794940363 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1208.6705379679336 rank 8 upper 1324.6034210201387 variance 874.6959163268912 votes 94 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/174/row` |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,433.65 | — | 74 / 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` \| 1433.6463929957558 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1428.1647924777062 rank 123 upper 1439.1279935138054 variance 7.822013886394524 votes 17221 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8640/row` |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,445.31 | — | 63 / 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` \| 1445.3107383391327 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1440.3893432035186 rank 106 upper 1450.232133474747 variance 6.304930291162178 votes 21217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1742/row` |  |  |  |  |  |  |
| [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 13.54% | 95% CI 8.7–18.38% | 15 / 30 | 1usd per problem | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 13.54 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 1.00 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 8.7–18.38% confidenceInterval95 4.84 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label GPT-5.2 (high) Source version apex--apex_2025 Observed 2026-10-21T16:52:38.728Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,281.69 | — | 45 / 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` \| 1281.6864642205219 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1270.0792879883302 rank 54 upper 1293.2936404527134 variance 35.07171269398381 votes 2888 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/861/row` |  |  |  |  |  |  |
| [Kangaroo 2025 1-2](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_1-2.md) | 80.21% | 95% CI 72.24–88.18% | 8 / 16 | 0.06usd per problem | [matharena · kangaroo--kangaroo_2025_1-2](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.21 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.059 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_1-2 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 72.24–88.18% confidenceInterval95 7.97 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_1-2 Observed 2026-10-21T16:52:31.513Z Evidence SHA-256 `a59a4c362e2d87350330706a01dd330e9a1ac7cc64a4de0bacbf1a439d8fcf90` Source locator `/table/rows/8` |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,372.1 | — | 81 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1372.103318758295 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1365.4326111511054 rank 140 upper 1378.7740263654844 variance 11.583708704854892 votes 9343 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4832/row` |  |  |  |  |  |  |
| [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,265.44 | — | 50 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1265.4406175506524 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1255.9855678358233 rank 64 upper 1274.8956672654813 variance 23.27187906539517 votes 4773 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/530/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) | 1,443.04 | — | 59 / 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` \| 1443.0366243357578 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1436.42081763144 rank 92 upper 1449.6524310400755 variance 11.393822084753056 votes 9757 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4374/row` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 43.33% | — | 86 / 212 | 1.39usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4333 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 1.393 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-2-2025-12-11-thinking modelType CoT Reasoning effort high sourceModelVersion gpt-5-2-2025-12-11-thinking-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.2 (High) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/106` |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,431.01 | — | 62 / 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` \| 1431.0142872424904 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1415.327568020095 rank 105 upper 1446.7010064648857 variance 64.05721665859295 votes 1536 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10869/row` |  |  |  |  |  |  |
| [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,242.8 | — | 48 / 82 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1242.7965010530527 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1236.7102406826095 rank 62 upper 1248.8827614234956 variance 9.642838053417119 votes 19022 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/61/row` |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,439.63 | — | 57 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.628347881121 \| rating \| reported \| Higher is better \| ### Configuration category math config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1428.9105857459133 rank 86 upper 1450.3461100163286 variance 29.902813110498126 votes 3125 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8998/row` |  |  |  |  |  |  |
| [Arena vision / chinese (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision.md) | 1,304.84 | — | 40 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1304.8361998345263 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1286.958139191658 rank 49 upper 1322.7142604773949 variance 83.20408138393873 votes 1351 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/249/row` |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,441.56 | — | 68 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.5578572436323 \| rating \| reported \| Higher is better \| ### Configuration category coding config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1435.5460711466976 rank 115 upper 1447.5696433405667 variance 9.408293505737758 votes 12238 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/924/row` |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,430.52 | — | 76 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1430.521259722747 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1424.648304277247 rank 127 upper 1436.3942151682463 variance 8.978777926503929 votes 13037 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3994/row` |  |  |  |  |  |  |
| [SWE-bench Multilingual](https://benchize.com/benchmarks/swe-bench%3Amultilingual.md) | 66.7% | — | 6 / 9 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 66.7 \| percent \| multilingual \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-5.2-2025-12-11"] Reasoning effort high sourceSubmission 20260213_mini-v2.0.0a0_gpt-5-2-high subset Multilingual system ["System: Attempts - 1"] ### Reported statistics instanceCalls 40.266666666666666 instanceCost 0.5364109905 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 5.2 Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/0/results/8` |  |  |  |  |  |  |
| [Arena vision style control / entity recognition](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition.md) | 1,201.3 | — | 18 / 34 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1201.2995680449712 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1159.3912331755416 rank 28 upper 1243.2079029144008 variance 457.19832321693224 votes 168 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/784/row` |  |  |  |  |  |  |
| [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,238.1 | — | 51 / 82 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1238.0989879616109 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1229.3160969263827 rank 67 upper 1246.8818789968389 variance 20.080698124664647 votes 7347 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/656/row` |  |  |  |  |  |  |
| [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 79.26% | 95% CI 73.46–85.06% | 9 / 24 | 0.76usd per problem | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.26 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.76 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 73.46–85.06% confidenceInterval95 5.80 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label GPT-5.2 (high) Source version apex--shortlist_2025 Observed 2026-10-21T16:52:39.300Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/9` |  |  |  |  |  |  |
| [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) | 1,452.28 | — | 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` \| 1452.2761200110044 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1445.209935054343 rank 109 upper 1459.342304967666 variance 12.997918804379175 votes 8273 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5606/row` |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,461.58 | — | 52 / 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` \| 1461.5842298046277 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1449.6138869291349 rank 73 upper 1473.5545726801206 variance 37.300701437941576 votes 2624 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5985/row` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 78.67% | — | 94 / 213 | 0.52usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7867 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.5196 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-2-2025-12-11-thinking modelType CoT Reasoning effort high sourceModelVersion gpt-5-2-2025-12-11-thinking-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.2 (High) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/102` |  |  |  |  |  |  |
| [τ-bench airline](https://benchize.com/benchmarks/sierra%3Aairline.md) | 83% | — | 2 / 8 | $0.11 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2_sierra_2026-02-26/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 83 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 78.33 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 75 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 72 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.11379 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-05","notes":"Evaluated using AllTools retrieval (BM25 + dense OpenAI text-embedding-3-large + sandboxed shell). User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking_knowledge domain only — other domains intentionally excluded from this comparison; the AllTools setting standardizes retrieval across models. banking_knowledge re-graded under tau2-bench v1.0.1 grading fixes on 2026-07-15 (extra-read logging #329, numeric-argument normalization #397, T077-T086 gold trajectories #402); scores prior to v1.0.1 are not comparable.","tau2_bench_version":"1.0.1","user_simulator":"gpt-5.2","verification":{"details":"Verified evaluation with full trajectory data available. Standard tau-bench scaffold.","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort high retrieval Not reported sourceSubmission gpt-5-2_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.424Z Evidence SHA-256 `343687b822edbcbff42a4d4632ecc6288a58d9817a7a02c8533081c5709c0ac6` Source locator `/results/airline` |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,437.2 | — | 61 / 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` \| 1437.2022298648776 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1433.6495074312281 rank 101 upper 1440.7549522985269 variance 3.28568840112546 votes 49646 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/100/row` |  |  |  |  |  |  |
| [Kangaroo 2025 11-12](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12.md) | 95.83% | 95% CI 92.25–99.41% | 6 / 16 | 0.05usd per problem | [matharena · kangaroo--kangaroo_2025_11-12](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.053 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.25–99.41% confidenceInterval95 3.58 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/8` |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,488.97 | — | 61 / 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` \| 1488.965003794444 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1482.8904237908678 rank 98 upper 1495.0395837980204 variance 9.605861716143785 votes 12238 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/907/row` |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,379.54 | — | 57 / 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` \| 1379.536345217452 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1357.55385896602 rank 103 upper 1401.5188314688844 variance 125.79327915510187 votes 786 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8336/row` |  |  |  |  |  |  |
| [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 72.8% | — | 5 / 63 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 72.8 \| percent \| verified \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-5-2"] Reasoning effort high sourceSubmission 20260217_mini-v2.0.0_gpt-5-2-high subset Verified system ["System: Attempts - 1"] ### Reported statistics instanceCalls 35.046 instanceCost 0.4735670177 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 5.2 Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/25` |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,423.9 | — | 64 / 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` \| 1423.9031581933114 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1419.4973970206167 rank 102 upper 1428.3089193660062 variance 5.052958372547672 votes 28429 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9832/row` |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,442.27 | — | 58 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1442.2673085696406 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1430.3420704344067 rank 87 upper 1454.1925467048743 variance 37.020129908964684 votes 2624 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5999/row` |  |  |  |  |  |  |
| [ArXivMath 01/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--january.md) | 67.93% | 95% CI 61.19–74.67% | 6 / 18 | 0.35usd per problem | [matharena · arxiv--january](https://matharena.ai/competition_tables/arxiv--january) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.93 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.35 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--january predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 61.19–74.67% confidenceInterval95 6.74 problems 23 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--january) Source matharena Original model label GPT-5.2 (high) Source version arxiv--january Observed 2026-10-21T16:52:27.447Z Evidence SHA-256 `e895f6ccd0711bb1a512b580bab39de8f977c57f83bf492527e4fc710315d706` Source locator `/table/rows/6` |  |  |  |  |  |  |
| [ArXivMath 12/2025](https://benchize.com/benchmarks/matharena%3Aarxiv--december.md) | 52.21% | 95% CI 46.27–58.15% | 4 / 12 | 0.51usd per problem | [matharena · arxiv--december](https://matharena.ai/competition_tables/arxiv--december) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.21 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.51 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--december predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 46.27–58.15% confidenceInterval95 5.94 problems 17 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--december) Source matharena Original model label GPT-5.2 (high) Source version arxiv--december Observed 2026-10-21T16:52:26.934Z Evidence SHA-256 `6bbceef2706ad55e793e81bd959f7c1ec869f0ad04c6aa9013b2ad7b1a0820e3` Source locator `/table/rows/3` |  |  |  |  |  |  |
| [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,256.91 | — | 49 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1256.9110095107055 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1250.5424604876744 rank 63 upper 1263.2795585337367 variance 10.558076645325908 votes 12905 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1081/row` |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,428.08 | — | 69 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1428.0790199605945 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1423.7012112075477 rank 115 upper 1432.4568287136412 variance 4.989044624143337 votes 29881 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3565/row` |  |  |  |  |  |  |
| [τ-bench telecom](https://benchize.com/benchmarks/sierra%3Atelecom.md) | 89.69% | — | 5 / 8 | $0.09 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2_sierra_2026-02-26/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 89.69 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 82.46 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 76.75 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 71.93 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.09312 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-05","notes":"Evaluated using AllTools retrieval (BM25 + dense OpenAI text-embedding-3-large + sandboxed shell). User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking_knowledge domain only — other domains intentionally excluded from this comparison; the AllTools setting standardizes retrieval across models. banking_knowledge re-graded under tau2-bench v1.0.1 grading fixes on 2026-07-15 (extra-read logging #329, numeric-argument normalization #397, T077-T086 gold trajectories #402); scores prior to v1.0.1 are not comparable.","tau2_bench_version":"1.0.1","user_simulator":"gpt-5.2","verification":{"details":"Verified evaluation with full trajectory data available. Standard tau-bench scaffold.","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort high retrieval Not reported sourceSubmission gpt-5-2_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.424Z Evidence SHA-256 `343687b822edbcbff42a4d4632ecc6288a58d9817a7a02c8533081c5709c0ac6` Source locator `/results/telecom` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,187elo | — | 51 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1187 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported Reasoning effort high sourceModelVersion honeycomb thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 169409 battles 469 losses 203 standardError Not reported winRate 56.7 wins 266 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-5.2 (High) Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/80` |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--final_answer_comps.md) | 72.03% | 95% CI 69.93–74.13% | 10 / 20 | 0.47usd per problem | [matharena · overall--final_answer_comps](https://matharena.ai/competition_tables/overall--final_answer_comps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.03 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.47 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--final_answer_comps predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 69.93–74.13% confidenceInterval95 2.10 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--final_answer_comps) Source matharena Original model label GPT-5.2 (high) Source version overall--final_answer_comps Observed 2026-10-21T16:52:34.395Z Evidence SHA-256 `8b08b20c1ac5aec9a829d234469bc39d40b0eb189790d84b7264c2756ffa161e` Source locator `/table/rows/11` |  |  |  |  |  |  |
| [ArXivMath 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--february.md) | 37.5% | 95% CI 29.11–45.89% | 15 / 20 | 0.34usd per problem | [matharena · arxiv--february](https://matharena.ai/competition_tables/arxiv--february) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.34 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--february predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 29.11–45.89% confidenceInterval95 8.39 problems 32 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--february) Source matharena Original model label GPT-5.2 (high) Source version arxiv--february Observed 2026-10-21T16:52:27.963Z Evidence SHA-256 `3bc5b0a1eb91a0bdaa3d0942ebf82327a8664334b225ae3b2dc1d8b4f57efa51` Source locator `/table/rows/15` |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,456.37 | — | 50 / 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` \| 1456.3670926373318 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1445.6486167919477 rank 70 upper 1467.0855684827156 variance 29.90679578007867 votes 3125 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8982/row` |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,425.1 | — | 81 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.098130891078 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1418.1229086474586 rank 136 upper 1432.073353134697 variance 12.665429363912388 votes 8273 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5633/row` |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,413.4 | — | 73 / 134 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1413.4011325428032 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1397.8123351985846 rank 126 upper 1428.9899298870218 variance 63.25997856075052 votes 1536 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10890/row` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,053elo | — | 81 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1053 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported Reasoning effort high sourceModelVersion honeycomb thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 120022 battles 342 losses 187 standardError Not reported winRate 45.3 wins 155 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-5.2 (High) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/129` |  |  |  |  |  |  |
| [BRUMO 2025](https://benchize.com/benchmarks/matharena%3Abrumo--brumo_2025.md) | 98.33% | 95% CI 96.04–100.62% | 4 / 25 | 0.08usd per problem | [matharena · brumo--brumo_2025](https://matharena.ai/competition_tables/brumo--brumo_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.084 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition brumo--brumo_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 96.04–100.62% confidenceInterval95 2.29 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/brumo--brumo_2025) Source matharena Original model label GPT-5.2 (high) Source version brumo--brumo_2025 Observed 2026-10-21T16:52:35.992Z Evidence SHA-256 `d1d1c126b1feff70b2bcc20a7adbf380d94c2aaab0704704cb01593d4e1958ff` Source locator `/table/rows/5` |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,450.81 | — | 46 / 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` \| 1450.8087342303809 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1433.5484867088762 rank 71 upper 1468.0689817518855 variance 77.55286686888829 votes 1183 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10218/row` |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,431.75 | — | 64 / 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` \| 1431.748178869258 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1423.9633434748366 rank 104 upper 1439.5330142636794 variance 15.77621027505492 votes 6311 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10487/row` |  |  |  |  |  |  |
| [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 71.8% | — | 8 / 63 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 71.8 \| percent \| verified \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-5.2-2025-12-11"] Reasoning effort high sourceSubmission 20251211_mini-v1.17.2_gpt-5.2-2025-12-11-high subset Verified system ["System: Attempts - 1"] ### Reported statistics instanceCalls 19.762 instanceCost 0.5202590036 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 5.2 Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/29` |  |  |  |  |  |  |
| [Arena vision / entity recognition (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aentity_recognition--config-vision.md) | 1,231.96 | — | 15 / 34 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1231.964074713659 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1190.8395148076202 rank 24 upper 1273.0886346196976 variance 440.2570758678018 votes 168 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/780/row` |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,422.98 | — | 53 / 117 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.9839846814903 \| rating \| reported \| Higher is better \| ### Configuration category polish config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1405.9569932357888 rank 93 upper 1440.0109761271917 variance 75.47092165356185 votes 1183 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10240/row` |  |  |  |  |  |  |
| [HMMT Nov 2025](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_nov_2025.md) | 95.83% | 95% CI 92.25–99.41% | 2 / 12 | 0.14usd per problem | [matharena · hmmt--hmmt_nov_2025](https://matharena.ai/competition_tables/hmmt--hmmt_nov_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_nov_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.25–99.41% confidenceInterval95 3.58 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_nov_2025) Source matharena Original model label GPT-5.2 (high) Source version hmmt--hmmt_nov_2025 Observed 2026-10-21T16:52:37.292Z Evidence SHA-256 `aa9287d733e27dde3646179a18070c07f558fb51926a8fe90cdf38985d6fce6d` Source locator `/table/rows/1` |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,452.25 | — | 66 / 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` \| 1452.2541092109482 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1441.5936316727123 rank 106 upper 1462.9145867491843 variance 29.58401655408105 votes 3506 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6418/row` |  |  |  |  |  |  |
| [Kangaroo 2025 5-6](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_5-6.md) | 80% | 95% CI 72.84–87.16% | 6 / 16 | 0.08usd per problem | [matharena · kangaroo--kangaroo_2025_5-6](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.081 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_5-6 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 72.84–87.16% confidenceInterval95 7.16 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_5-6 Observed 2026-10-21T16:52:32.526Z Evidence SHA-256 `9460cafccce0b6f3ba1f90e1090be31d6cf94dd10b9157819abc97efe624b126` Source locator `/table/rows/6` |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,454.37 | — | 48 / 132 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1454.3650358748123 \| rating \| reported \| Higher is better \| ### Configuration category french config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1437.4384593432574 rank 78 upper 1471.2916124063672 variance 74.58338262931554 votes 1439 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2915/row` |  |  |  |  |  |  |
| [Arena vision style control / humor](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahumor.md) | 1,217.39 | — | 42 / 63 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1217.3850627216582 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1193.6313214098102 rank 59 upper 1241.138804033506 variance 146.88175837538506 votes 681 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/984/row` |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,434.23 | — | 77 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.2306129422482 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1429.1044312873637 rank 133 upper 1439.3567945971326 variance 6.840562292979613 votes 18414 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6833/row` |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,475.15 | — | 55 / 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` \| 1475.1450245369504 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1465.4117751977976 rank 82 upper 1484.878273876103 variance 24.661501559712118 votes 3997 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2552/row` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,182elo | — | 52 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1182 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported Reasoning effort high sourceModelVersion honeycomb thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 154999 battles 302 losses 139 standardError Not reported winRate 54 wins 163 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-5.2 (High) Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/84` |  |  |  |  |  |  |
| [HMMT Feb 2025](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2025.md) | 98.33% | 95% CI 96.04–100.62% | 2 / 34 | 0.16usd per problem | [matharena · hmmt--hmmt_feb_2025](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.16 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 96.04–100.62% confidenceInterval95 2.29 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2025) Source matharena Original model label GPT-5.2 (high) Source version hmmt--hmmt_feb_2025 Observed 2026-10-21T16:52:35.608Z Evidence SHA-256 `8554225c26eb7a3c2649943ee7cf6b404ec1f7441b20fbdcfccbf35b9a864864` Source locator `/table/rows/2` |  |  |  |  |  |  |
| [Kangaroo 2025 3-4](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_3-4.md) | 73.96% | 95% CI 65.18–82.74% | 4 / 16 | 0.08usd per problem | [matharena · kangaroo--kangaroo_2025_3-4](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.96 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.079 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_3-4 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 65.18–82.74% confidenceInterval95 8.78 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_3-4 Observed 2026-10-21T16:52:32.012Z Evidence SHA-256 `38fec99c55752fef6703c9ed49d9e1e204b235f2bd78d5ee47725dac9e5da89c` Source locator `/table/rows/4` |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,375.65 | — | 77 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1375.6460542246355 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1368.348138755 rank 137 upper 1382.9439696942711 variance 13.86441263278262 votes 7659 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1358/row` |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,385.95 | — | 79 / 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` \| 1385.9451674724214 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1378.5326201647458 rank 137 upper 1393.357714780097 variance 14.303383207580197 votes 7659 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1358/row` |  |  |  |  |  |  |
| [CMIMC 2025](https://benchize.com/benchmarks/matharena%3Acmimc--cmimc_2025.md) | 95.62% | 95% CI 92.45–98.79% | 1 / 21 | 0.14usd per problem | [matharena · cmimc--cmimc_2025](https://matharena.ai/competition_tables/cmimc--cmimc_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 95.62 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition cmimc--cmimc_2025 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 92.45–98.79% confidenceInterval95 3.17 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/cmimc--cmimc_2025) Source matharena Original model label GPT-5.2 (high) Source version cmimc--cmimc_2025 Observed 2026-10-21T16:52:36.936Z Evidence SHA-256 `d5d48c1f54a744d7ff2244bae3258963afdb1ab36fb20464ea9cf47138a1555e` Source locator `/table/rows/2` |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,426.91 | — | 64 / 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` \| 1426.91245189355 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1421.337863276828 rank 100 upper 1432.487040510272 variance 8.089645027112354 votes 15296 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7633/row` |  |  |  |  |  |  |
| [Kangaroo 2025 7-8](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_7-8.md) | 89.17% | 95% CI 83.61–94.73% | 8 / 15 | 0.06usd per problem | [matharena · kangaroo--kangaroo_2025_7-8](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.058 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_7-8 predicted false Reasoning effort high sourceModelName GPT-5.2 (high) sourceModelVersion openai/gpt-52-high thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 83.61–94.73% confidenceInterval95 5.56 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) Source matharena Original model label GPT-5.2 (high) Source version kangaroo--kangaroo_2025_7-8 Observed 2026-10-21T16:52:33.033Z Evidence SHA-256 `197887eb5244aa6bce3570bd9eb25bbb0bb6ec95568339536d94e2859f0ee8c1` Source locator `/table/rows/10` |  |  |  |  |  |  |
| [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,245.79 | — | 51 / 82 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1245.7853715616577 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1239.7475448396067 rank 68 upper 1251.8231982837087 variance 9.489975873000857 votes 19022 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/67/row` |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,409.15 | — | 65 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.1543763988914 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1403.6182890126768 rank 106 upper 1414.690463785106 variance 7.97828767100165 votes 15296 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7639/row` |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,443.86 | — | 39 / 129 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.8606938281478 \| rating \| reported \| Higher is better \| ### Configuration category german config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1423.0800122539463 rank 64 upper 1464.6413754023497 variance 112.41477439821607 votes 834 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3200/row` |  |  |  |  |  |  |
| [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,213.13 | — | 57 / 70 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1213.1308943841377 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1196.1661749356422 rank 79 upper 1230.0956138326333 variance 74.91989876756243 votes 1330 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/441/row` |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,442.13 | — | 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` \| 1442.1294699129448 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1435.2684438352285 rank 103 upper 1448.9904959906612 variance 12.254115177680966 votes 9239 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9418/row` |  |  |  |  |  |  |
| [Arena vision style control / captioning](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acaptioning.md) | 1,262.12 | — | 3 / 22 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1262.1193656790242 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1204.614467044801 rank 3 upper 1319.6242643132475 variance 860.8222868662131 votes 94 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/169/row` |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,419.34 | — | 70 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.3427690003546 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1412.5196348571544 rank 117 upper 1426.165903143555 variance 12.119135388178558 votes 9239 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9432/row` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,155elo | — | 84 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1155 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text Reasoning effort high sourceModelVersion honeycomb thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 152483 battles 2971 losses 1498 standardError Not reported winRate 49.6 wins 1473 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-5.2 (High) Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/121` |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,463.63 | — | 37 / 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` \| 1463.6313038232477 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1442.5090841020515 rank 54 upper 1484.7535235444436 variance 116.14029637570566 votes 834 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3190/row` |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,150elo | SE ±5.51 | 80 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1150 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text Reasoning effort high sourceModelVersion honeycomb thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±5.51 averageGenerationTimeMs 152056 battles 4150 losses 2056 standardError 5.5102 winRate 50.5 wins 2094 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-5.2 (High) Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/115` |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,436.16 | — | 38 / 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` \| 1436.1574556984522 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1406.7106844783764 rank 52 upper 1465.604226918528 variance 225.7247508723268 votes 446 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8002/row` |  |  |  |  |  |  |

[Next page](https://benchize.com/models/gpt-5-2-high.md?cursor=d3ab90752a024d82a47224d9b6c469ba3f34549215b6fe23d563796b8036d111)

---
Cite as: GPT-5.2High — Benchize, https://benchize.com/models/gpt-5-2-high (retrieved 2026-10-21)