← All comparisons
Claude Sonnet 4.6 (Non-reasoning, Low Effort) vs Ministral 3 14B
Anthropic vs Mistral — side-by-side benchmark comparison
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | Ministral 3 14B | |
|---|---|---|
| Intelligence Index | 42.6 | 16.0 |
| Coding Index | 43.0 | 10.9 |
| Math Index | — | 30.0 |
| Output speed (tok/s) | 54.9 | 90.6 |
| Blended price ($/1M) | $6.56 | $0.20 |
| Time to first token (s) | 1.13s | 0.37s |
| aime | — | — |
| aime 25 | — | 30.0% |
| artificial analysis coding index | 43.00 | 10.90 |
| artificial analysis intelligence index | 42.60 | 16.00 |
| artificial analysis math index | — | 30.00 |
| gpqa | 79.7% | 57.2% |
| hle | 10.8% | 4.6% |
| ifbench | 42.4% | 32.0% |
| lcr | 58.7% | 22.0% |
| livecodebench | — | 35.1% |
| math 500 | — | — |
| mmlu pro | — | 69.3% |
| scicode | 44.1% | 23.6% |
| tau2 | 78.9% | 27.2% |
| terminalbench hard | 42.4% | 4.5% |
Benchmark data from Artificial Analysis.