← All comparisons
Llama 3.2 Instruct 1B vs Claude 4.1 Opus (Non-reasoning)
Meta vs Anthropic — side-by-side benchmark comparison
| Llama 3.2 Instruct 1B | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 6.3 | 36.0 |
| Coding Index | 0.6 | — |
| Math Index | 0.0 | — |
| Output speed (tok/s) | 89.7 | 44.7 |
| Blended price ($/1M) | $0.05 | $32.81 |
| Time to first token (s) | 0.59s | 1.63s |
| aime | 0.0% | — |
| aime 25 | 0.0% | — |
| artificial analysis coding index | 60.0% | — |
| artificial analysis intelligence index | 6.30 | 36.00 |
| artificial analysis math index | 0.0% | — |
| gpqa | 19.6% | — |
| hle | 5.3% | — |
| ifbench | 22.8% | — |
| lcr | 5.0% | — |
| livecodebench | 1.9% | — |
| math 500 | 14.0% | — |
| mmlu pro | 20.0% | — |
| scicode | 1.7% | — |
| tau2 | 0.0% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.