← All comparisons
Llama 3 Instruct 8B vs Claude 4.1 Opus (Non-reasoning)
Meta vs Anthropic — side-by-side benchmark comparison
| Llama 3 Instruct 8B | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 6.4 | 36.0 |
| Coding Index | 4.0 | — |
| Math Index | — | — |
| Output speed (tok/s) | 83.3 | 44.7 |
| Blended price ($/1M) | $0.07 | $32.81 |
| Time to first token (s) | 0.47s | 1.63s |
| aime | 0.0% | — |
| aime 25 | — | — |
| artificial analysis coding index | 4.00 | — |
| artificial analysis intelligence index | 6.40 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 29.6% | — |
| hle | 5.1% | — |
| ifbench | 24.6% | — |
| lcr | 0.0% | — |
| livecodebench | 9.6% | — |
| math 500 | 49.9% | — |
| mmlu pro | 40.5% | — |
| scicode | 11.9% | — |
| tau2 | 0.0% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.