o1
o1 (OpenAI) was released on Dec 17, 2024. In the Epoch AI capability ranking (ECI), it ranks #114 out of 267 models, with 141.84. On Arena, which measures human preference in blind comparisons, it has 1,383 ELO points (#185). Against models of the same generation, its best result is on Dtbench: 74.7%, #1 of 30.
Where o1 stands out and where it falls behind, by the numbers
o1 has published results on 24 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Mar 22, 2024 and Mar 17, 2025 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.
See all 24 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 76.8% | #3 / 45 | #91 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 73.3% | #2 / 39 | #90 / 168 | 100.0% GPT-5.5 |
| Dtbench | 74.7% | #1 / 30 | #86 / 148 | 98.9% Claude Opus 5.5 |
| Lmca | 22.27 | #1 / 16 | #89 / 121 | 68.23 Claude Opus 5.5 |
| WeirdML | 47.6% | #1 / 20 | #53 / 112 | 93.6% GPT-6 Astra |
| Frontiermath Tiers 1 3 V2 | 14.7% | #2 / 5 | #79 / 86 | 93.7% GPT-6 Astra |
| ARC-AGI | 30.7% | #2 / 6 | #66 / 81 | 98.5% Claude Fable 5 |
| SimpleQA Verified | 41.1% | #1 / 4 | #44 / 81 | 76.0% Gemini 4 Argon |
| Chess puzzles | 10.0% | #2 / 4 | #71 / 80 | 76.0% GPT-6 Astra |
| SimpleBench | 41.7% | #2 / 16 | #47 / 74 | 81.9% Claude Fable 5 |
| MATH level 5 | 94.7% | #2 / 39 | #12 / 73 | 98.1% GPT-5 |
| FrontierMath | 9.3% | #2 / 12 | #37 / 65 | 51.7% GPT-5.5 |
| Hle | 8.0% | #2 / 8 | #29 / 39 | 54.8% GPT-6 Astra |
| Aider Polyglot | 61.70 | #1 / 14 | #11 / 38 | 88.00 GPT-5 |
| Creative writing (Lech Mazur) | 7.02 | #10 / 17 | #30 / 38 | 8.60 GPT-5 |
| EnigmaEval | 5.7% | #1 / 8 | #20 / 36 | 39.3% Claude Fable 5 |
| LiveBench | 75.67 | #3 / 27 | #5 / 32 | 82.35 Gemini 2.5 Pro (Jun 2025) |
| Fiction.liveBench | 53.1% | #3 / 6 (tied with 1) | #17 / 31 | 100.0% o3 |
| METR: time horizon | 38.83 | #2 / 7 | #19 / 29 | 719 Claude Opus 4.6 |
| GeoBench | 3,925 | #2 / 11 | #7 / 24 | 4,333 Gemini 3 Flash |
| VPCT | 37.0% | #4 / 6 | #18 / 22 | 91.0% Gemini 3 Pro |
| Cybench | 10.0% | #6 / 10 (tied with 1) | #14 / 19 | 93.0% Claude Opus 4.6 |
| CAD-Eval | 56.0% | #1 / 8 | #4 / 14 | 74.0% o3 |
| Spatialviz Bench | 41.4% | #1 / 3 | #2 / 7 | 44.7% Gemini 2.5 Pro (Jun 2025) |
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 o1 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 |
|---|---|---|---|---|---|
| o1 | OpenAI | 141.84 | 1,383 | n/a | Dec 17, 2024 |
| Claude Sonnet 4 | Anthropic | 141.67 | 1,414 | n/a | May 22, 2025 |
| DeepSeek-R1 (May 2025) | DeepSeek | 141.27 | 1,400 | n/a | May 28, 2025 |
| Claude 3.7 Sonnet | Anthropic | 141.14 | 1,360 | n/a | Feb 24, 2025 |
| Grok-3 mini | xAI | 140.33 | 1,394 | n/a | Jun 24, 2025 |
| Kimi K2 Instruct | Moonshot | 140.13 | n/a | n/a | Jul 12, 2025 |
| DeepSeek-V3.1 | DeepSeek | 139.91 | 1,469 | n/a | Aug 21, 2025 |
o1 or Claude Sonnet 4?
Claude Sonnet 4 is the model from another lab closest to o1 in capability. Across the 18 tests both took, this is the score:
| Test | o1 | Claude Sonnet 4 |
|---|---|---|
| Cybench | 10.0% | 35.0% |
| FrontierMath | 9.3% | 4.1% |
| METR: time horizon | 38.83 | 74.94 |
| EnigmaEval | 5.7% | 3.1% |
| GeoBench | 3,925 | 2,468 |
| Fiction.liveBench | 53.1% | 36.4% |
| ARC-AGI | 30.7% | 40.0% |
| Lmca | 22.27 | 29.00 |
| Creative writing (Lech Mazur) | 7.02 | 8.14 |
| MATH level 5 | 94.7% | 84.4% |
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 |
|---|---|---|---|---|---|
| o3 | Apr 16, 2025 | 146.87 | n/a | n/a | API access |
| o4-mini | Apr 16, 2025 | 145.60 | n/a | n/a | API access |
| GPT-4.1 | Apr 14, 2025 | 136.77 | n/a | n/a | API access |
| GPT-4.1 mini | Apr 14, 2025 | 135.00 | n/a | n/a | API access |
| GPT-4.1 nano | Apr 14, 2025 | 129.63 | n/a | n/a | API access |
| GPT-4.5 | Feb 27, 2025 | 136.73 | n/a | n/a | API access |
| o3-mini | Jan 31, 2025 | 140.33 | 1,379 | n/a | API access |
| o1 | Dec 17, 2024 | 141.84 | 1,383 | n/a | API access |
| o1-mini | Sep 12, 2024 | 135.82 | 1,362 | n/a | API access |
Have you used o1? 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 o1
Where does o1 rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, o1 ranks #114 out of 267 models, with an ECI of 141.84. 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 o1 better than Claude Sonnet 4?
Across the 18 tests both models took and Epoch AI compiled, o1 comes out ahead on 10, behind on 8 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 o1 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 o1 are: Dtbench (#1 of 30); WeirdML (#1 of 20); Lmca (#1 of 16). 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