← All comparisons
Ministral 3 14B vs Claude 4.1 Opus (Non-reasoning)
Mistral vs Anthropic — side-by-side benchmark comparison
| Ministral 3 14B | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 16.0 | 36.0 |
| Coding Index | 10.9 | — |
| Math Index | 30.0 | — |
| Output speed (tok/s) | 90.6 | 44.7 |
| Blended price ($/1M) | $0.20 | $32.81 |
| Time to first token (s) | 0.37s | 1.63s |
| aime | — | — |
| aime 25 | 30.0% | — |
| artificial analysis coding index | 10.90 | — |
| artificial analysis intelligence index | 16.00 | 36.00 |
| artificial analysis math index | 30.00 | — |
| gpqa | 57.2% | — |
| hle | 4.6% | — |
| ifbench | 32.0% | — |
| lcr | 22.0% | — |
| livecodebench | 35.1% | — |
| math 500 | — | — |
| mmlu pro | 69.3% | — |
| scicode | 23.6% | — |
| tau2 | 27.2% | — |
| terminalbench hard | 4.5% | — |
Benchmark data from Artificial Analysis.