← All comparisons
Llama 3.1 Instruct 405B vs Claude 4.1 Opus (Reasoning)
Meta vs Anthropic — side-by-side benchmark comparison
| Llama 3.1 Instruct 405B | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 17.4 | 42.0 |
| Coding Index | 14.5 | 36.5 |
| Math Index | 3.0 | 80.3 |
| Output speed (tok/s) | 37.5 | 44.5 |
| Blended price ($/1M) | $3.69 | $32.81 |
| Time to first token (s) | 0.63s | 8.55s |
| aime | 21.3% | — |
| aime 25 | 3.0% | 80.3% |
| artificial analysis coding index | 14.50 | 36.50 |
| artificial analysis intelligence index | 17.40 | 42.00 |
| artificial analysis math index | 3.00 | 80.30 |
| gpqa | 51.5% | 80.9% |
| hle | 4.2% | 11.9% |
| ifbench | 39.0% | 55.4% |
| lcr | 24.3% | 66.3% |
| livecodebench | 30.5% | 65.4% |
| math 500 | 70.3% | — |
| mmlu pro | 73.2% | 88.0% |
| scicode | 29.9% | 40.9% |
| tau2 | 19.0% | 71.4% |
| terminalbench hard | 6.8% | 34.3% |
Benchmark data from Artificial Analysis.