GPT-4o (May 2024)
GPT-4o (May 2024) (OpenAI) was released on May 13, 2024. In the Epoch AI capability ranking (ECI), it ranks #165 out of 267 models, with 129.05. Against models of the same generation, its best result is on MMLU: 88.1%, #1 of 49.
Where GPT-4o (May 2024) stands out and where it falls behind, by the numbers
GPT-4o (May 2024) has published results on 33 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Aug 17, 2023 and Aug 11, 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 33 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 49.2% | #2 / 25 | #129 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 6.4% | #4 / 19 | #144 / 168 | 100.0% GPT-5.5 |
| Dtbench | 64.5% | #1 / 20 | #100 / 148 | 98.9% Claude Opus 5.5 |
| Lmca | 16.59 | #2 / 9 | #100 / 121 | 68.23 Claude Opus 5.5 |
| CritPt | 0.0% | #1 / 2 (tied with 1) | #91 / 112 | 32.3% GPT-5.6 Sol |
| WeirdML | 25.1% | #1 / 13 | #92 / 112 | 93.6% GPT-6 Astra |
| MMLU | 88.1% | #1 / 49 | #1 / 92 | 88.1% GPT-4o (May 2024) |
| Frontiermath Tiers 1 3 V2 | 0.4% | #3 / 4 | #85 / 86 | 93.7% GPT-6 Astra |
| ARC-AGI 2 | 0.0% | #1 / 2 (tied with 1) | #76 / 83 | 95.0% GPT-6 Astra |
| ARC-AGI | 4.5% | #1 / 1 | #77 / 81 | 98.5% Claude Fable 5 |
| SimpleQA Verified | 26.0% | #1 / 3 | #64 / 81 | 76.0% Gemini 4 Argon |
| Chess puzzles | 6.0% | #1 / 3 | #75 / 80 | 76.0% GPT-6 Astra |
| SimpleBench | 17.8% | #4 / 5 | #72 / 74 | 81.9% Claude Fable 5 |
| MATH level 5 | 53.3% | #1 / 24 | #40 / 73 | 98.1% GPT-5 |
| FrontierMath | 0.3% | #1 / 1 | #61 / 65 | 51.7% GPT-5.5 |
| ForecastBench | 57.70 | #5 / 11 | #48 / 62 | 62.50 o3 |
| Hle | 2.7% | #1 / 1 | #39 / 39 | 54.8% GPT-6 Astra |
| Aider Polyglot | 23.10 | #1 / 2 | #31 / 38 | 88.00 GPT-5 |
| Creative writing (Lech Mazur) | 8.18 | #1 / 2 | #11 / 38 | 8.60 GPT-5 |
| EnigmaEval | 0.8% | #2 / 2 | #33 / 36 | 39.3% Claude Fable 5 |
| BALROG | 32.3% | #1 / 5 | #16 / 32 | 68.3% GPT-6 Astra |
| LiveBench | 55.33 | #1 / 7 | #15 / 32 | 82.35 Gemini 2.5 Pro (Jun 2025) |
| SWE-bench Verified | 31.0% | #1 / 1 | #32 / 32 | 83.5% Claude Opus 4.7 |
| METR: time horizon | 9.17 | #1 / 4 | #24 / 29 | 719 Claude Opus 4.6 |
| Gso | 0.0% | #1 / 1 | #28 / 28 | 88.2% Claude Fable 5.1 |
| GeoBench | 3,696 | #1 / 2 | #14 / 24 | 4,333 Gemini 3 Flash |
| VPCT | 40.0% | #1 / 2 | #12 / 22 | 91.0% Gemini 3 Pro |
| Cybench | 12.5% | #1 / 5 | #13 / 19 | 93.0% Claude Opus 4.6 |
| CAD-Eval | 26.0% | #1 / 2 | #12 / 14 | 74.0% o3 |
| The Agent Company | 16.7% | #1 / 4 | #8 / 14 | 52.4% DeepSeek-V3.2-Exp |
| GDPval | 9.9% | #1 / 1 | #11 / 11 | 49.7% GPT-5.2 |
| ScienceQA | 88.5% | #1 / 2 | #1 / 6 | 88.5% GPT-4o (May 2024) |
| Video Mme | 71.9% | #1 / 2 | #3 / 6 | 75.0% Gemini 1.5 Pro (Sept 2024) |
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-4o (May 2024) 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 |
|---|---|---|---|---|---|
| Phi-4 | Microsoft Research | 130.43 | 1,231 | n/a | Dec 12, 2024 |
| Gemini 1.5 Flash (Sep 2024) | Google DeepMind | 129.37 | n/a | n/a | Sep 24, 2024 |
| GPT-4o (May 2024) | OpenAI | 129.05 | n/a | n/a | May 13, 2024 |
| Qwen2.5-72B | Alibaba | 129.00 | n/a | n/a | Sep 19, 2024 |
| Llama 3.1-405B | Meta AI | 128.76 | n/a | n/a | Jul 23, 2024 |
| 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-4o (May 2024) or Qwen2.5-72B?
Qwen2.5-72B is the model from another lab closest to GPT-4o (May 2024) in capability. Across the 13 tests both took, this is the score:
| Test | GPT-4o (May 2024) | Qwen2.5-72B |
|---|---|---|
| BALROG | 32.3% | 16.2% |
| METR: time horizon | 9.17 | 5.17 |
| WeirdML | 25.1% | 16.0% |
| The Agent Company | 16.7% | 11.8% |
| AIME 2024 and 2025 (OTIS) | 6.4% | 8.1% |
| Lmca | 16.59 | 13.42 |
| MATH level 5 | 53.3% | 63.2% |
| GeoBench | 3,696 | 3,448 |
| MMLU | 88.1% | 85.3% |
| Dtbench | 64.5% | 62.9% |
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-4.1 | Apr 14, 2025 | 136.77 | 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 |
| GPT-4o mini | Jul 18, 2024 | 126.58 | n/a | n/a | API access |
| GPT-4o (May 2024) | May 13, 2024 | 129.05 | n/a | n/a | API access |
| GPT-4 Turbo (Apr 2024) | Apr 9, 2024 | 127.25 | n/a | n/a | API access |
| GPT-3.5 Turbo (Nov 2023) | Nov 6, 2023 | 118.58 | n/a | n/a | API access |
Have you used GPT-4o (May 2024)? 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-4o (May 2024)
Where does GPT-4o (May 2024) rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, GPT-4o (May 2024) ranks #165 out of 267 models, with an ECI of 129.05. 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-4o (May 2024) better than Qwen2.5-72B?
Across the 13 tests both models took and Epoch AI compiled, GPT-4o (May 2024) comes out ahead on 10, behind on 3 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-4o (May 2024) 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-4o (May 2024) are: MMLU (#1 of 49); MATH level 5 (#1 of 24); Dtbench (#1 of 20). 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