← All comparisons
Claude 3 Haiku vs Llama 3.1 Tulu3 405B
Anthropic vs Allen Institute for AI — side-by-side benchmark comparison
| Claude 3 Haiku | Llama 3.1 Tulu3 405B | |
|---|---|---|
| Intelligence Index | 12.3 | 14.1 |
| Coding Index | 6.7 | — |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.50 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | 1.0% | 13.3% |
| aime 25 | — | — |
| artificial analysis coding index | 6.70 | — |
| artificial analysis intelligence index | 12.30 | 14.10 |
| artificial analysis math index | — | — |
| gpqa | 37.4% | 51.6% |
| hle | 3.9% | 3.5% |
| ifbench | 36.1% | — |
| lcr | 21.0% | — |
| livecodebench | 15.4% | 29.1% |
| math 500 | 39.4% | 77.8% |
| mmlu pro | — | 71.6% |
| scicode | 18.6% | 30.2% |
| tau2 | 21.1% | — |
| terminalbench hard | 0.8% | — |
Benchmark data from Artificial Analysis.