GPT-5 Pro
GPT-5 Pro (OpenAI) was released on Oct 7, 2025. In the Epoch AI capability ranking (ECI), it ranks #53 out of 267 models, with 150.74. Against models of the same generation, its best result is on EnigmaEval: 18.8%, #1 of 21.
Where GPT-5 Pro stands out and where it falls behind, by the numbers
GPT-5 Pro has published results on 10 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Jan 10, 2025 and Jan 5, 2026 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
It is not in the bottom half of its generation on any test with 6 or more models compared.
See all 10 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| WeirdML | 60.4% | #7 / 41 | #31 / 112 | 93.6% GPT-6 Astra |
| Frontiermath Tiers 1 3 V2 | 55.8% | #3 / 17 | #45 / 86 | 93.7% GPT-6 Astra |
| ARC-AGI 2 | 18.3% | #6 / 36 | #44 / 83 | 95.0% GPT-6 Astra |
| ARC-AGI | 70.2% | #7 / 35 | #44 / 81 | 98.5% Claude Fable 5 |
| Chess puzzles | 48.0% | #2 / 18 (tied with 1) | #17 / 80 | 76.0% GPT-6 Astra |
| SimpleBench | 61.6% | #4 / 31 | #20 / 74 | 81.9% Claude Fable 5 |
| Frontiermath Tier 4 V2 | 19.5% | #4 / 13 | #46 / 67 | 100.0% GPT-6.1 Sol |
| FrontierMath tier 4 | 14.6% | #3 / 26 | #10 / 48 | 39.6% GPT-5.5 Pro |
| Hle | 31.6% | #2 / 21 | #12 / 39 | 54.8% GPT-6 Astra |
| EnigmaEval | 18.8% | #1 / 21 | #7 / 36 | 39.3% Claude Fable 5 |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare GPT-5 Pro with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| GLM-5.2 | Z.ai (Zhipu AI) | 151.86 | n/a | 73.2 | Jun 16, 2026 |
| Gemini 3 Flash | Google DeepMind | 151.80 | 1,511 | n/a | Dec 17, 2025 |
| Kimi K2.6 | Moonshot | 150.92 | 1,521 | 70.5 | Apr 20, 2026 |
| GPT-5 Pro | OpenAI | 150.74 | n/a | n/a | Oct 7, 2025 |
| Claude Opus 4.5 | Anthropic | 150.17 | 1,504 | 72.6 | Nov 24, 2025 |
| GLM-5.1 | Z.ai (Zhipu AI) | 149.99 | 1,514 | n/a | Apr 7, 2026 |
| Kimi K2.7 Code | Moonshot | 149.87 | n/a | 68.4 | Jun 12, 2026 |
GPT-5 Pro or Kimi K2.6?
Kimi K2.6 is the model from another lab closest to GPT-5 Pro in capability. Across the 5 tests both took, this is the score:
| Test | GPT-5 Pro | Kimi K2.6 |
|---|---|---|
| Chess puzzles | 48.0% | 20.0% |
| Frontiermath Tier 4 V2 | 19.5% | 25.6% |
| WeirdML | 60.4% | 55.9% |
| Frontiermath Tiers 1 3 V2 | 55.8% | 57.2% |
| FrontierMath tier 4 | 14.6% | 14.6% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from OpenAI
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| GPT-5.2 Pro | Dec 11, 2025 | 156.03 | n/a | n/a | API access |
| GPT-5.2 | Dec 11, 2025 | 153.46 | 1,454 | 74.6 | API access |
| GPT-5.1 | Nov 13, 2025 | 149.76 | 1,495 | n/a | API access |
| GPT-5 Pro | Oct 7, 2025 | 150.74 | n/a | n/a | API access |
| GPT-5 | Aug 7, 2025 | 150.00 | 1,436 | n/a | API access |
| GPT-5 mini | Aug 7, 2025 | 145.43 | 1,406 | n/a | API access |
| GPT-5 nano | Aug 7, 2025 | 139.33 | 1,356 | n/a | API access |
| gpt-oss-120b | Aug 5, 2025 | 140.00 | 1,385 | n/a | Open weights (unrestricted) |
| gpt-oss-20b | Aug 5, 2025 | 137.81 | 1,315 | n/a | Open weights (unrestricted) |
Have you used GPT-5 Pro? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about GPT-5 Pro
Where does GPT-5 Pro rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, GPT-5 Pro ranks #53 out of 267 models, with an ECI of 150.74. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
Is GPT-5 Pro better than Kimi K2.6?
Across the 5 tests both models took and Epoch AI compiled, GPT-5 Pro comes out ahead on 3, behind on 2 and tied on 0. It is a test-by-test count with no weighting: a win in math counts the same as a win in coding. To choose between the two, look at the tests that resemble your own use.
What is GPT-5 Pro best at?
Against models of the same generation (released up to 9 months before and up to 3 months after it), the best relative results of GPT-5 Pro are: EnigmaEval (#1 of 21); Hle (#2 of 21); FrontierMath tier 4 (#3 of 26). The yardstick is its position among the models of that period that took the same test.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking