# GPT-5 > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5. OpenAI Canonical URL: https://benchize.com/models/gpt-5 Last updated: Thu, 22 Oct 2026 07:32:33 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 | | | --- | --- | --- | --- | --- | --- | --- | | [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 74.4% | — | 4 / 63 | — | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 74.4 \| percent \| verified \| Higher is better \| ### Configuration agent Prometheus-v1.2.1 agentOrganization EuniAI models ["gpt-5-2025-08-07"] Reasoning effort Not reported sourceSubmission 20251015_Prometheus_v1.2.1_gpt5 subset Verified system ["System: Attempts - 2+"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT-5 Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/18` | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,672 | — | 10 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1672 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5 ### Reported statistics coverageCount 16 draws 2 judged 71 losses 31 rank 15 ratingDeviation 28 wins 38 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/14` | | | | | | | | [τ-bench airline (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aairline.md) | 62.5% | — | 6 / 14 | $0.13 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5_sierra_2025-08-09/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 62.5 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 55.33333333333332 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 51 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 48 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.13399991125 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-08-09","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-5_sierra_2025-08-09 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5_sierra_2025-08-09/submission.json) Source sierra Original model label GPT-5 Evaluated 2025-10-02 Observed 2026-10-21T16:55:02.770Z Evidence SHA-256 `288a3ec7ff0fe305344fa7fd866a692754a67ad61fb5198c0b64ee4987a88636` Source locator `/results/airline` | | | | | | | | [τ-bench retail (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aretail.md) | 81.58% | — | 4 / 14 | $0.11 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5_sierra_2025-08-09/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 81.57894736842105 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 71.78362573099416 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 64.69298245614036 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 58.77192982456141 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.10552710142543861 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-08-09","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-5_sierra_2025-08-09 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5_sierra_2025-08-09/submission.json) Source sierra Original model label GPT-5 Evaluated 2025-10-02 Observed 2026-10-21T16:55:02.770Z Evidence SHA-256 `288a3ec7ff0fe305344fa7fd866a692754a67ad61fb5198c0b64ee4987a88636` Source locator `/results/retail` | | | | | | | | [τ-bench telecom (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Atelecom.md) | 95.83% | — | 5 / 10 | $0.16 | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5_sierra_2025-08-09/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 95.83333333333334 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_2` \| 91.95906432748538 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_3` \| 88.37719298245614 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `pass_4` \| 85.08771929824562 \| percent \| consistent_success_across_k_trials \| Higher is better \| \| `cost` \| 0.16471152192982458 \| USD \| source_reported \| Lower is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-08-09","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-5_sierra_2025-08-09 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/gpt-5_sierra_2025-08-09/submission.json) Source sierra Original model label GPT-5 Evaluated 2025-10-02 Observed 2026-10-21T16:55:02.770Z Evidence SHA-256 `288a3ec7ff0fe305344fa7fd866a692754a67ad61fb5198c0b64ee4987a88636` Source locator `/results/telecom` | | | | | | | | [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 OpenHands agentOrganization OpenHands models ["openai/gpt-5-2025-08-07"] Reasoning effort Not reported sourceSubmission 20250807_openhands_gpt5 subset Verified system ["System: Attempts - 1"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT-5 Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/28` | | | | | | | | [PRBench Legal](https://benchize.com/benchmarks/scale%3Aprbench-legal.md) | 48.96source score | CI 48.93–48.99 | 10 / 26 | — | [scale](https://labs.scale.com/leaderboard/prbench-legal) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 48.96127165 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 48.93–48.99 contaminationWarning Not reported rank 14 reportedConfidenceHalfWidth 0.02813447719 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-legal) Source scale Original model label gpt-5 Observed 2026-10-22T03:30:10.599Z Evidence SHA-256 `c086b601b5cff78b7934cfbcf79f15db48cd423c4e62e56a185b447b03c28f3c` Source locator `/rows/13` | | | | | | | | [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 71.2% | — | 10 / 63 | — | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 71.2 \| percent \| verified \| Higher is better \| ### Configuration agent Prometheus-v1.2 agentOrganization EuniAI models ["gpt-5-2025-08-07"] Reasoning effort Not reported sourceSubmission 20250929_Prometheus_v1.2_gpt5 subset Verified system ["System: Attempts - 1"] ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT-5 Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/33` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 91.48% | — | 42 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.48 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.67 \| percent \| category \| Higher is better \| \| `creative_writing` \| 86.87 \| percent \| category \| Higher is better \| \| `language` \| 91.5 \| percent \| category \| Higher is better \| \| `utility` \| 93.53 \| percent \| category \| Higher is better \| \| `reasoning` \| 89.34 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.9 \| percent \| category \| Higher is better \| \| `rule_following` \| 77.13 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.92 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5 Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/52` | | | | | | | | [PRBench Finance](https://benchize.com/benchmarks/scale%3Aprbench-finance.md) | 51.32source score | CI 51.15–51.49 | 5 / 22 | — | [scale](https://labs.scale.com/leaderboard/prbench-finance) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 51.32272595 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-5 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 51.15–51.49 contaminationWarning Not reported rank 7 reportedConfidenceHalfWidth 0.1713853993 ### Source [Original source](https://labs.scale.com/leaderboard/prbench-finance) Source scale Original model label gpt-5 Observed 2026-10-22T03:30:10.417Z Evidence SHA-256 `52572a2526d41cba3e52146e6063412a3850897b7608a0745f62baae712ab29b` Source locator `/rows/6` | | | | | | | --- Cite as: GPT-5 — Benchize, https://benchize.com/models/gpt-5 (retrieved 2026-10-22)