Claude 3 Opus
Claude 3 Opus (Anthropic) was released on Feb 29, 2024. In the Epoch AI capability ranking (ECI), it ranks #175 out of 267 models, with 126.91. On Arena, which measures human preference in blind comparisons, it has 1,264 ELO points (#287). Against models of the same generation, its best result is on WinoGrande: 88.5%, #1 of 35.
Where Claude 3 Opus stands out and where it falls behind, by the numbers
Claude 3 Opus has published results on 16 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Jun 4, 2023 and May 29, 2024 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 16 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 47.2% | #2 / 19 | #139 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 4.7% | #3 / 15 | #147 / 168 | 100.0% GPT-5.5 |
| Dtbench | 61.6% | #2 / 18 (tied with 1) | #109 / 148 | 98.9% Claude Opus 5.5 |
| Lmca | 17.00 | #1 / 5 | #99 / 121 | 68.23 Claude Opus 5.5 |
| WeirdML | 19.2% | #2 / 8 | #98 / 112 | 93.6% GPT-6 Astra |
| MMLU | 84.6% | #2 / 53 | #9 / 92 | 88.1% GPT-4o (May 2024) |
| SimpleQA Verified | 12.6% | #2 / 2 | #76 / 81 | 76.0% Gemini 4 Argon |
| Chess puzzles | 3.0% | #2 / 2 | #76 / 80 | 76.0% GPT-6 Astra |
| SimpleBench | 23.5% | #2 / 3 | #64 / 74 | 81.9% Claude Fable 5 |
| MATH level 5 | 37.5% | #3 / 18 | #51 / 73 | 98.1% GPT-5 |
| ForecastBench | 58.40 | #3 / 11 | #43 / 62 | 62.50 o3 |
| WinoGrande | 88.5% | #1 / 35 | #2 / 61 | 89.2% Llama 3.1-405B |
| EnigmaEval | 0.8% | #1 / 2 | #32 / 36 | 39.3% Claude Fable 5 |
| LiveBench | 49.16 | #2 / 4 | #19 / 32 | 82.35 Gemini 2.5 Pro (Jun 2025) |
| METR: time horizon | 3.95 | #3 / 3 | #28 / 29 | 719 Claude Opus 4.6 |
| Cybench | 10.0% | #2 / 4 | #14 / 19 | 93.0% Claude Opus 4.6 |
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 Claude 3 Opus 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 |
|---|---|---|---|---|---|
| Mistral Large 2 (Nov 2024) | Mistral AI | 128.53 | n/a | n/a | Nov 18, 2024 |
| Qwen2.5-32B | Alibaba | 128.53 | n/a | n/a | Sep 17, 2024 |
| GPT-4 Turbo (Apr 2024) | OpenAI | 127.25 | n/a | n/a | Apr 9, 2024 |
| Claude 3 Opus | Anthropic | 126.91 | 1,264 | n/a | Feb 29, 2024 |
| GPT-4o mini | OpenAI | 126.58 | n/a | n/a | Jul 18, 2024 |
| Llama 3.1-70B | Meta AI | 125.94 | n/a | n/a | Jul 23, 2024 |
| Llama 3.2 90B | Meta AI | 125.51 | n/a | n/a | Sep 24, 2024 |
Claude 3 Opus or GPT-4o mini?
GPT-4o mini is the model from another lab closest to Claude 3 Opus in capability. Across the 11 tests both took, this is the score:
| Test | Claude 3 Opus | GPT-4o mini |
|---|---|---|
| SimpleBench | 23.5% | 10.7% |
| Lmca | 17.00 | 10.37 |
| WeirdML | 19.2% | 11.8% |
| SimpleQA Verified | 12.6% | 8.3% |
| AIME 2024 and 2025 (OTIS) | 4.7% | 6.9% |
| MATH level 5 | 37.5% | 52.6% |
| GPQA Diamond | 47.2% | 37.7% |
| LiveBench | 49.16 | 41.26 |
| Dtbench | 61.6% | 54.4% |
| MMLU | 84.6% | 81.8% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from Anthropic
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Claude 3.7 Sonnet | Feb 24, 2025 | 141.14 | 1,360 | n/a | API access |
| Claude 3.5 Sonnet (October 2024) | Oct 22, 2024 | 133.53 | 1,342 | n/a | API access |
| Claude 3.5 Haiku | Oct 22, 2024 | 127.17 | 1,286 | n/a | API access |
| Claude 3 Haiku | Mar 7, 2024 | 118.39 | 1,206 | n/a | API access |
| Claude 3 Opus | Feb 29, 2024 | 126.91 | 1,264 | n/a | API access |
| Claude 3 Sonnet | Feb 29, 2024 | 120.72 | 1,226 | n/a | API access |
| Claude 2.1 | Nov 21, 2023 | 119.30 | n/a | n/a | API access |
| Claude Instant | Aug 9, 2023 | 120.31 | n/a | n/a | API access |
| Claude 2 | Jul 11, 2023 | 120.15 | n/a | n/a | API access |
Have you used Claude 3 Opus? 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 Claude 3 Opus
Where does Claude 3 Opus rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Claude 3 Opus ranks #175 out of 267 models, with an ECI of 126.91. 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 Claude 3 Opus better than GPT-4o mini?
Across the 11 tests both models took and Epoch AI compiled, Claude 3 Opus comes out ahead on 8, behind on 2 and tied on 1. 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 Claude 3 Opus 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 Claude 3 Opus are: WinoGrande (#1 of 35); MMLU (#2 of 53); GPQA Diamond (#2 of 19). 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