# GPT-4.1

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-4-1. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-4-1.

OpenAI

Canonical URL: https://benchize.com/models/gpt-4-1
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

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

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [τ-bench airline (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aairline.md) | 56% | — | 10 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-4-1_openai_2024-06-20/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 56 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 47.8 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 42.4 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 38.1 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-06-09","notes":"Original evaluation from tau2-bench paper","tau2_bench_version":"0.1.3","user_simulator":"gpt-4.1-2025-04-14","verification":{"details":"Verified evaluation with full trajectory data available","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission gpt-4-1_openai_2024-06-20 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-4-1_openai_2024-06-20/submission.json) Source sierra Original model label GPT-4.1 Evaluated 2025-06-09 Observed 2026-10-21T16:55:01.514Z Evidence SHA-256 `69d0798527fc2cabf9168795e99dcec78128b440b5a4ad3abd1d788cc6db7954` Source locator `/results/airline` |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 86.82% | — | 84 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.82 \| percent \| reported \| Higher is better \| \| `tooling` \| 97.71 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.24 \| percent \| category \| Higher is better \| \| `language` \| 93.91 \| percent \| category \| Higher is better \| \| `utility` \| 90.57 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.4 \| percent \| category \| Higher is better \| \| `text_editing` \| 94.4 \| percent \| category \| Higher is better \| \| `rule_following` \| 66.78 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.6 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-4.1 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/109` |  |  |  |  |  |  |
| [MultiNRC](https://benchize.com/benchmarks/scale%3Amultinrc.md) | 21.23source score | CI 18.76–23.7 | 10 / 15 | — | [scale](https://labs.scale.com/leaderboard/multinrc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 21.23 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 18.76–23.7 contaminationWarning Not reported rank 34 reportedConfidenceHalfWidth 2.47 ### Source [Original source](https://labs.scale.com/leaderboard/multinrc) Source scale Original model label GPT-4.1 Observed 2026-10-21T16:35:36.736Z Evidence SHA-256 `a4931a13575ec92cd4993e96d4e87f8ef58149c485b7b54bb8558d7762620f8a` Source locator `/rows/33` |  |  |  |  |  |  |
| [Humanity’s Last Exam (HLE)](https://benchize.com/benchmarks/hle.md) | 5.4source score | CI 4.51–6.29 | 15 / 17 | — | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 5.4 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 4.51–6.29 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 49 reportedConfidenceHalfWidth 0.89 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam) Source scale Original model label GPT-4.1 Observed 2026-10-21T16:35:32.694Z Evidence SHA-256 `9970bf9ee4f6b6b167633a94634adae7ac9c906447d6db087a8dc9877c1b71e0` Source locator `/rows/48` |  |  |  |  |  |  |
| [τ-bench retail (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aretail.md) | 74% | — | 9 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-4-1_openai_2024-06-20/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 74 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 64.2 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 58.1 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 52.3 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-06-09","notes":"Original evaluation from tau2-bench paper","tau2_bench_version":"0.1.3","user_simulator":"gpt-4.1-2025-04-14","verification":{"details":"Verified evaluation with full trajectory data available","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission gpt-4-1_openai_2024-06-20 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-4-1_openai_2024-06-20/submission.json) Source sierra Original model label GPT-4.1 Evaluated 2025-06-09 Observed 2026-10-21T16:55:01.514Z Evidence SHA-256 `69d0798527fc2cabf9168795e99dcec78128b440b5a4ad3abd1d788cc6db7954` Source locator `/results/retail` |  |  |  |  |  |  |
| [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,179.5elo | CI 1,152–1,207 | 32 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1179.5 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 64.8 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion gpt-4.1 ### Reported statistics Uncertainty Confidence interval: 1,152–1,207 confidenceIntervalHigh 1207.0 confidenceIntervalLow 1152.0 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label gpt-4.1 Source version eqbench3 Observed 2026-10-21T16:35:00.608Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/44` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,000elo | — | 99 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1000 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion gpt-4.1 variationName public ### Reported statistics averageGenerationTimeMs 65597 battles 155 losses 78 standardError Not reported winRate 49.7 wins 77 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-4.1 Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/152` |  |  |  |  |  |  |
| [Humanity's Last Exam (Text Only)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only.md) | 4.97source score | CI 4.05–5.89 | 23 / 25 | — | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 4.97 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 4.05–5.89 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. Sampled at temperature 0.3. rank 56 reportedConfidenceHalfWidth 0.92 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) Source scale Original model label GPT-4.1 Observed 2026-10-21T16:35:33.193Z Evidence SHA-256 `4004825ae58bdcc249c0d26dab811842c6d172b2a67bc35e69949fbf12ead757` Source locator `/rows/55` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 5.5% | — | 204 / 213 | 0.04usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.055 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.039 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-4.1 modelType Base LLM sourceModelVersion gpt-4-1-2025-04-14 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-4.1 Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/17` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,039elo | — | 105 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1039 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gpt-4.1 variationName public ### Reported statistics averageGenerationTimeMs 71487 battles 1146 losses 547 standardError Not reported winRate 52.3 wins 599 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-4.1 Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/164` |  |  |  |  |  |  |
| [BuzzBench](https://benchize.com/benchmarks/eq-bench%3Abuzzbench.md) | 67.1% | CI 66.35–67.86% | 2 / 15 | — | [eq bench · buzzbench](https://eqbench.com/buzzbench.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 67.1 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion gpt-4.1 ### Reported statistics Uncertainty Confidence interval: 66.35–67.86% confidenceIntervalHigh 67.86 confidenceIntervalLow 66.35 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label gpt-4.1 Source version buzzbench Observed 2026-10-21T16:35:02.926Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/24` |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,419.7elo | — | 61 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1419.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.80 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-4.1 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-4.1 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/76` |  |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 76.31% | — | 18 / 39 | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 76.31 \| percent \| overall \| Higher is better \| \| `stability` \| 0.727 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.819 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.576 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion gpt-4.1 ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label gpt-4.1 Source version judgemark-v2 Observed 2026-10-21T16:35:03.564Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/0` |  |  |  |  |  |  |
| [PRBench Legal](https://benchize.com/benchmarks/scale%3Aprbench-legal.md) | 36.48source score | CI 36.44–36.53 | 25 / 26 | — | [scale](https://labs.scale.com/leaderboard/prbench-legal) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 36.48357264 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 36.44–36.53 contaminationWarning Not reported rank 39 reportedConfidenceHalfWidth 0.04821631431 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-4.1 Observed 2026-10-21T16:35:35.197Z Evidence SHA-256 `9e2ca4e9350870cf508bf5fff603d0b795c81f7974a0ab980312bbbfa0785067` Source locator `/rows/38` |  |  |  |  |  |  |
| [VISTA](https://benchize.com/benchmarks/scale%3Avisual_language_understanding.md) | 45.34source score | CI 44.43–46.25 | 6 / 16 | — | [scale](https://labs.scale.com/leaderboard/visual_language_understanding) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 45.34 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 44.43–46.25 contaminationWarning Not reported rank 29 reportedConfidenceHalfWidth 0.91 ### Source [Original source](https://labs.scale.com/leaderboard/visual_language_understanding) Source scale Original model label GPT-4.1 Observed 2026-10-21T16:35:38.974Z Evidence SHA-256 `469e2d64808796dc35f1a8b8b0abe7daefeb7c5ee06fa9b6ba8b34c42d4b19b5` Source locator `/rows/28` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 850elo | — | 109 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 850 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion gpt-4.1 variationName public ### Reported statistics averageGenerationTimeMs 67785 battles 181 losses 125 standardError Not reported winRate 30.9 wins 56 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-4.1 Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/165` |  |  |  |  |  |  |
| [MultiChallenge](https://benchize.com/benchmarks/scale%3Amultichallenge.md) | 39.43source score | CI 38.49–40.37 | 10 / 11 | — | [scale](https://labs.scale.com/leaderboard/multichallenge) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 39.43 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 38.49–40.37 contaminationWarning Not reported rank 30 reportedConfidenceHalfWidth 0.9393 ### Source [Original source](https://labs.scale.com/leaderboard/multichallenge) Source scale Original model label gpt-4.1 Observed 2026-10-21T16:35:37.135Z Evidence SHA-256 `92e84e933979bccb14193567e45702ffc95189cc48216f6af220e7e235bfa3a0` Source locator `/rows/29` |  |  |  |  |  |  |
| [Fortress](https://benchize.com/benchmarks/scale%3Afortress.md) | 53.02source score | CI 49.51–56.53 | 6 / 31 | — | [scale](https://labs.scale.com/leaderboard/fortress) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 53.02 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 49.51–56.53 contaminationWarning ORS score: 2.87 rank 59 reportedConfidenceHalfWidth 3.51 ### Source [Original source](https://labs.scale.com/leaderboard/fortress) Source scale Original model label GPT-4.1 Observed 2026-10-21T16:35:37.552Z Evidence SHA-256 `875f1c5b1112c4b84f3d17df72771ebee5c293c542cbb8ab3399e35c4f82ffa5` Source locator `/rows/58` |  |  |  |  |  |  |
| [PRBench Finance](https://benchize.com/benchmarks/scale%3Aprbench-finance.md) | 34.32source score | CI 34.06–34.58 | 20 / 22 | — | [scale](https://labs.scale.com/leaderboard/prbench-finance) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 34.3200519 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-4.1 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 34.06–34.58 contaminationWarning Not reported rank 35 reportedConfidenceHalfWidth 0.2569233566 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-finance) Source scale Original model label gpt-4.1 Observed 2026-10-21T16:35:34.798Z Evidence SHA-256 `948d67409f0ae9c93fd41428f634cfc93c7815a21f43690cecb9095c9d3ec8f1` Source locator `/rows/34` |  |  |  |  |  |  |
| [τ-bench telecom (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Atelecom.md) | 34% | — | 10 / 10 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-4-1_openai_2024-06-20/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 34 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 27.6 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 23.8 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 20.4 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-06-09","notes":"Original evaluation from tau2-bench paper","tau2_bench_version":"0.1.3","user_simulator":"gpt-4.1-2025-04-14","verification":{"details":"Verified evaluation with full trajectory data available","modified_prompts":false,"omitted_questions":false}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission gpt-4-1_openai_2024-06-20 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-4-1_openai_2024-06-20/submission.json) Source sierra Original model label GPT-4.1 Evaluated 2025-06-09 Observed 2026-10-21T16:55:01.514Z Evidence SHA-256 `69d0798527fc2cabf9168795e99dcec78128b440b5a4ad3abd1d788cc6db7954` Source locator `/results/telecom` |  |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 27% | — | 51 / 62 | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 thinkingEnabled Not reported ### Reported statistics rank 88th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label GPT-4.1 Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/89` |  |  |  |  |  |  |
| [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 39.58% | — | 52 / 63 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 39.58 \| percent \| verified \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-4.1-20250414"] Reasoning effort Not reported sourceSubmission 20250726_mini-v1.0.0_gpt-4.1-2025-04-14 subset Verified system ["System: Attempts - 1"] ### Reported statistics instanceCalls 19.544 instanceCost 0.146313124 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 4.1 Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/139` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 0.42% | — | 198 / 212 | 0.07usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0042 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0691 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-4.1 modelType Base LLM sourceModelVersion gpt-4-1-2025-04-14 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-4.1 Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/19` |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,026elo | SE ±8.85 | 102 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1026 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion gpt-4.1 variationName public ### Reported statistics Uncertainty Standard error: ±8.85 averageGenerationTimeMs 72709 battles 1747 losses 858 standardError 8.8516 winRate 50.9 wins 889 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-4.1 Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/158` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,079elo | — | 91 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1079 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion gpt-4.1 variationName public ### Reported statistics averageGenerationTimeMs 97202 battles 181 losses 74 standardError Not reported winRate 59.1 wins 107 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-4.1 Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/137` |  |  |  |  |  |  |
| [SWE-bench Multimodal](https://benchize.com/benchmarks/swe-bench%3Amultimodal.md) | 31.14% | — | 6 / 14 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 31.14 \| percent \| multimodal \| Higher is better \| ### Configuration agent GUIRepair agentOrganization GUIRepair models ["gpt-4.1-2025-04-14"] Reasoning effort Not reported sourceSubmission 20250531_GUIRepair_gpt41 subset Multimodal system ["System: Attempts - 1"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT-4.1 Observed 2026-10-21T14:54:06.913Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/4/results/6` |  |  |  |  |  |  |
| [MASK](https://benchize.com/benchmarks/scale%3Amask.md) | 51.13source score | CI 50.1–52.16 | 15 / 25 | — | [scale](https://labs.scale.com/leaderboard/mask) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 51.13 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-4.1 sourceModelVersion gpt-4.1-2025-04-14 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 50.1–52.16 contaminationWarning Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. rank 50 reportedConfidenceHalfWidth 1.03 ### Source [Original source](https://labs.scale.com/leaderboard/mask) Source scale Original model label GPT-4.1 Observed 2026-10-21T16:35:38.046Z Evidence SHA-256 `506198f10b9789b267cc2a11dcdfedc27067703da430d78b374b2c5dffb8ec7d` Source locator `/rows/49` |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,546 | — | 49 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1546 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_4_1 ### Reported statistics coverageCount 27 draws 3 judged 75 losses 31 rank 61 ratingDeviation 28 wins 41 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-4.1 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/59` |  |  |  |  |  |  |

---
Cite as: GPT-4.1 — Benchize, https://benchize.com/models/gpt-4-1 (retrieved 2026-10-21)