Updated daily at 05:00 UTC
- Released
- 5 Apr 2025
- Status
- Legacy
- Context
- 1M
- Max output
- —
- Input per 1M tokens
- —
- Output per 1M tokens
- —
- Open weights
- Yes
- License
- llama-4
- Parameters
- 401.58B, 17B active
- Knowledge cutoff
- Aug 2024
- Reasoning
- No
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 16.0 | 86 | 2 of 4 |
| Coding & software engineering | 15.6 | Not ranked | 1 of 5 |
| Human preference | 39.6 | Not ranked | 1 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 61.9% | Third party | — | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.1587 | Third party | — | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| SimpleBench | Score (AVG@5) | 27.7% | Third party | — | — | SimpleBench Leaderboard via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 67.0% | Independent | — | 8 Apr 2025 | Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tiers 1-3 (v1) | Accuracy | 0.7% | Independent | — | 8 Apr 2025 | Epoch AI |
| MATH Level 5 | Accuracy | 73.0% | Independent | — | 8 Apr 2025 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 20.6% | Independent | — | 8 Apr 2025 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Aider Polyglot | Percent correct | 15.6% | Third party | — | — | https://aider.chat/docs/leaderboards/ via Epoch AI |
| WeirdML (v2) | Average accuracy | 24.5% | Third party | — | — | https://htihle.github.io/weirdml.html via Epoch AI |
Long context
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Fiction.LiveBench | % correct at 16K tokens (Epoch's column) | 46.2% | Third party | — | — | Fiction.live leaderboard via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GeoBench | Country accuracy | 52.0% | Third party | — | — | GeoBench leaderboard via Epoch AI |
Writing
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| LLM Creative Story-Writing Benchmark V1 (Lech Mazur) | Mean rubric score (percent of the 10-point scale) | 62.0% | Third party | — | — | lechmazur/writing Github repository via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Text Arena (arena.ai) | Arena score (Elo scale) | 1327 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 39266 | Independent | — | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1145 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 6925 | Independent | — | 28 Sep 2026 | Arena |
Other Llama versions
- Llama 4 Scout5 Apr 2025
- Llama 3.3 70B6 Dec 2024
- Llama 3.2 11B Vision25 Sep 2024
- Llama 3.2 1B25 Sep 2024
- Llama 3.2 3B25 Sep 2024
- Llama 3.2 90B Vision25 Sep 2024
- Llama 3.1 405B23 Jul 2024
- Llama 3.1 70B23 Jul 2024
- Llama 3.1 8B23 Jul 2024
- Llama 3 70B18 Apr 2024
- Llama 3 8B18 Apr 2024
- Llama 2 13B18 Jul 2023
- Llama 2 70B18 Jul 2023
- Llama 2 7B18 Jul 2023
- LLaMA 13B24 Feb 2023
- LLaMA 33B24 Feb 2023
- LLaMA 65B24 Feb 2023
- LLaMA 7B24 Feb 2023
- Llama 3.3 8B—