Llama 3.3 70B: benchmarks and ranking
Llama 3.3 70B (Meta) — overall rank: #152 / 153, overall score: 11.0 (90% interval 5.9–19.6), leaderboards: 2. Released: 2024-12-06 · Price (in/out): $0.71 / $0.72
Rank on each leaderboard
| Leaderboard | Rank | Published value |
|---|---|---|
| Artificial Analysis | Not rated | — |
| LiveBench | Not rated | — |
| Epoch AI | #151 / 230 | 126.18 |
| ARC Prize (ARC-AGI) | Not rated | — |
| Scale AI SEAL | Not rated | — |
| Vals AI | Not rated | — |
| Terminal-Bench | Not rated | — |
| EQ-Bench | Not rated | — |
| SimpleBench | #105 / 112 | 19.9 |
| BenchLM.ai | Not rated | — |
Domain scores
- Coding: 17.3
- Reasoning: 11.9
- Math: 14.2
- Knowledge: 27.7
- Writing: 18.1
- Instructions: 8.2
- Chat & EQ: 9.0
- Business: 41.4
- Japanese: 27.6