# GPT-5.2Non-thinking > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-2-off. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-2-off. OpenAI Canonical URL: https://benchize.com/models/gpt-5-2-off Last updated: Thu, 22 Oct 2026 08:20:15 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 | | | --- | --- | --- | --- | --- | --- | --- | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,113elo | — | 51 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1113 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 45945 battles 397 losses 220 standardError Not reported winRate 44.6 wins 177 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/72` | | | | | | | | [τ-bench retail](https://benchize.com/benchmarks/sierra%3Aretail.md) | 75% | — | 7 / 8 | $0.05 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 75 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 62.13450292397662 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 53.07017543859649 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 45.614035087719294 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.048219267434210525 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-26","notes":"Evaluated using GPT-5.2 with reasoning_effort: none. User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking domain evaluated with retrieval_config: qwen_embeddings. 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 none retrieval Not reported sourceSubmission gpt-5-2-none_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.671Z Evidence SHA-256 `e1be4bac436e8115f9253697d68b71867f17cfcb2bef5dfa6a756c0a89a70dab` Source locator `/results/retail` | | | | | | | | [τ-bench banking knowledge](https://benchize.com/benchmarks/sierra%3Abanking_knowledge.md) | 12.63% | — | 18 / 19 | $0.24 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 12.63 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 7.22 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 5.15 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 4.12 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.2433424974226804 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-26","notes":"Evaluated using GPT-5.2 with reasoning_effort: none. User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking domain evaluated with retrieval_config: qwen_embeddings. 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 none retrieval qwen_embeddings sourceSubmission gpt-5-2-none_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.671Z Evidence SHA-256 `e1be4bac436e8115f9253697d68b71867f17cfcb2bef5dfa6a756c0a89a70dab` Source locator `/results/banking_knowledge` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,183 | Range 1,137.3–1,226.8 | 90 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1183 \| rating \| reported \| Higher is better \| \| `overall` \| 71.37 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 61.05 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 73.66 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 77.8 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 77.82 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 20.06 \| source_score \| rubric \| Higher is better \| \| `slop` \| 77.62 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.19 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 82.29 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 74.98 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 70.04 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 74.82 \| source_score \| rubric \| Higher is better \| ### Configuration provider openai Reasoning effort none scoreScope 10_task_current sourceConfiguration gpt-5-2 thinkingEnabled false ### Reported statistics Uncertainty Reported interval: 1,137.3–1,226.8 interval [1137.3,1226.8] rank 93 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label GPT-5.2 (no reasoning) Evaluated 2026-10-10 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/92` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,175elo | — | 57 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1175 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 139982 battles 1744 losses 864 standardError Not reported winRate 50.5 wins 880 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/88` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,073elo | — | 74 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1073 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 131387 battles 5009 losses 2964 standardError Not reported winRate 40.8 wins 2045 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/118` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,169elo | SE ±2.19 | 64 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1169 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics Uncertainty Standard error: ±2.19 averageGenerationTimeMs 167045 battles 28884 losses 14510 standardError 2.1926 winRate 49.8 wins 14374 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/97` | | | | | | | | [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 38% | — | 91 / 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` \| 0.38 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.23 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.0 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.1 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort none suite v2 thinkingEnabled false ### Reported statistics acceptedCount 23 answeredCount 100 clearCount 38 errorCount 0 partialCount 39 rank 103 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 2026-10-22T03:10:12.603Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/102` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,176elo | — | 55 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1176 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 180737 battles 4111 losses 1976 standardError Not reported winRate 51.9 wins 2135 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/86` | | | | | | | | [τ-bench telecom](https://benchize.com/benchmarks/sierra%3Atelecom.md) | 57.24% | — | 8 / 8 | $0.05 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 57.23684210526315 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 42.83625730994152 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 35.526315789473685 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 30.701754385964914 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.04937742280701755 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-26","notes":"Evaluated using GPT-5.2 with reasoning_effort: none. User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking domain evaluated with retrieval_config: qwen_embeddings. 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 none retrieval Not reported sourceSubmission gpt-5-2-none_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.671Z Evidence SHA-256 `e1be4bac436e8115f9253697d68b71867f17cfcb2bef5dfa6a756c0a89a70dab` Source locator `/results/telecom` | | | | | | | | [τ-bench airline](https://benchize.com/benchmarks/sierra%3Aairline.md) | 52.5% | — | 8 / 8 | $0.05 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 52.5 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 35.66666666666667 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 27 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 22 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.053692803500000004 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 1.0.1 harness tau-bench methodology {"evaluation_date":"2026-05-26","notes":"Evaluated using GPT-5.2 with reasoning_effort: none. User simulator: gpt-5.2 with reasoning_effort: low. 4 trials. Seed: 300. Banking domain evaluated with retrieval_config: qwen_embeddings. 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 none retrieval Not reported sourceSubmission gpt-5-2-none_sierra_2026-02-26 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5-2-none_sierra_2026-02-26/submission.json) Source sierra Original model label GPT-5.2 Evaluated 2026-02-26 Observed 2026-10-21T16:54:47.671Z Evidence SHA-256 `e1be4bac436e8115f9253697d68b71867f17cfcb2bef5dfa6a756c0a89a70dab` Source locator `/results/airline` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,130elo | — | 47 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1130 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 40150 battles 6005 losses 2753 standardError Not reported winRate 54.1 wins 3252 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/77` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,184elo | — | 62 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1184 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 175987 battles 17722 losses 8638 standardError Not reported winRate 51.3 wins 9084 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/97` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,184elo | — | 55 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1184 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion mumble thinkingEnabled false variationName public ### Reported statistics averageGenerationTimeMs 145965 battles 1284 losses 637 standardError Not reported winRate 50.4 wins 647 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label GPT-5.2 (None) Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/83` | | | | | | | --- Cite as: GPT-5.2Non-thinking — Benchize, https://benchize.com/models/gpt-5-2-off (retrieved 2026-10-22)