Llama 3.1-405B
Llama 3.1-405B (Meta AI) was released on Jul 23, 2024. In the Epoch AI capability ranking (ECI), it ranks #167 out of 267 models, with 128.76. Against models of the same generation, its best result is on WinoGrande: 89.2%, #1 of 33.
Where Llama 3.1-405B stands out and where it falls behind, by the numbers
Llama 3.1-405B has published results on 16 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between Oct 27, 2023 and Oct 21, 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.
See all 16 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| GPQA Diamond | 50.9% | #3 / 34 | #128 / 173 | 96.4% Gemini 4 Argon |
| AIME 2024 and 2025 (OTIS) | 9.7% | #4 / 27 | #134 / 168 | 100.0% GPT-5.5 |
| Dtbench | 61.4% | #5 / 26 | #111 / 148 | 98.9% Claude Opus 5.5 |
| WeirdML | 21.4% | #5 / 17 | #97 / 112 | 93.6% GPT-6 Astra |
| MMLU | 84.5% | #5 / 52 | #10 / 92 | 88.1% GPT-4o (May 2024) |
| SimpleBench | 23.0% | #4 / 8 | #65 / 74 | 81.9% Claude Fable 5 |
| MATH level 5 | 49.8% | #8 / 31 | #43 / 73 | 98.1% GPT-5 |
| ARC (AI2) | 95.3% | #1 / 29 | #1 / 65 | 95.3% DeepSeek-V3 (Mar 2025) |
| ForecastBench | 59.90 | #1 / 14 | #30 / 62 | 62.50 o3 |
| WinoGrande | 89.2% | #1 / 33 | #1 / 61 | 89.2% Llama 3.1-405B |
| HellaSwag | 89.2% | #1 / 19 | #2 / 51 | 95.3% GPT-4 (Mar 2023) |
| PIQA | 85.9% | #3 / 13 | #3 / 43 | 88.7% GPT-4o mini |
| BIG-Bench Hard | 82.9% | #2 / 15 | #3 / 41 | 89.2% Gemini 1.5 Pro (Sept 2024) |
| TriviaQA | 82.7% | #2 / 12 | #10 / 32 | 87.6% Llama 2-70B |
| Cybench | 7.5% | #4 / 6 (tied with 1) | #17 / 19 | 93.0% Claude Opus 4.6 |
| The Agent Company | 14.1% | #2 / 6 | #9 / 14 | 52.4% DeepSeek-V3.2-Exp |
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 Llama 3.1-405B 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 |
|---|---|---|---|---|---|
| GPT-4.1 nano | OpenAI | 129.63 | n/a | n/a | Apr 14, 2025 |
| 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 |
Llama 3.1-405B or Mistral Large 2 (Nov 2024)?
Mistral Large 2 (Nov 2024) is the model from another lab closest to Llama 3.1-405B in capability. Across the 7 tests both took, this is the score:
| Test | Llama 3.1-405B | Mistral Large 2 (Nov 2024) |
|---|---|---|
| AIME 2024 and 2025 (OTIS) | 9.7% | 8.5% |
| MMLU | 84.5% | 80.0% |
| ForecastBench | 59.90 | 57.10 |
| SimpleBench | 23.0% | 22.5% |
| MATH level 5 | 49.8% | 50.3% |
| GPQA Diamond | 50.9% | 51.3% |
| Dtbench | 61.4% | 61.2% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from Meta AI
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Llama 4 Scout | Apr 5, 2025 | 129.65 | n/a | n/a | Open weights (restricted use) |
| Llama 3.3 70B | Dec 6, 2024 | 127.34 | n/a | n/a | Open weights (restricted use) |
| Llama 3.2 90B | Sep 24, 2024 | 125.51 | n/a | n/a | Open weights (restricted use) |
| Llama 3.2 1B | Sep 24, 2024 | 102.04 | n/a | n/a | Open weights (restricted use) |
| Llama 3.1-405B | Jul 23, 2024 | 128.76 | n/a | n/a | Open weights (restricted use) |
| Llama 3.1-70B | Jul 23, 2024 | 125.94 | n/a | n/a | Open weights (restricted use) |
| Llama 3.1-8B | Jul 23, 2024 | 116.61 | n/a | n/a | Open weights (restricted use) |
| Llama 3-70B | Apr 18, 2024 | 122.94 | n/a | n/a | Open weights (restricted use) |
| Llama 3-8B | Apr 18, 2024 | 116.49 | n/a | n/a | Open weights (restricted use) |
Have you used Llama 3.1-405B? 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 Llama 3.1-405B
Where does Llama 3.1-405B rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Llama 3.1-405B ranks #167 out of 267 models, with an ECI of 128.76. 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 Llama 3.1-405B better than Mistral Large 2 (Nov 2024)?
Across the 7 tests both models took and Epoch AI compiled, Llama 3.1-405B comes out ahead on 5, 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 Llama 3.1-405B 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 Llama 3.1-405B are: WinoGrande (#1 of 33); ARC (AI2) (#1 of 29); HellaSwag (#1 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