← All comparisons
Claude 4.1 Opus (Reasoning) vs Grok 3 mini Reasoning (high)
Anthropic vs xAI — side-by-side benchmark comparison
| Claude 4.1 Opus (Reasoning) | Grok 3 mini Reasoning (high) | |
|---|---|---|
| Intelligence Index | 42.0 | 32.1 |
| Coding Index | 36.5 | 25.2 |
| Math Index | 80.3 | 84.7 |
| Output speed (tok/s) | 44.5 | 56.8 |
| Blended price ($/1M) | $32.81 | $0.35 |
| Time to first token (s) | 8.55s | 0.42s |
| aime | — | 93.3% |
| aime 25 | 80.3% | 84.7% |
| artificial analysis coding index | 36.50 | 25.20 |
| artificial analysis intelligence index | 42.00 | 32.10 |
| artificial analysis math index | 80.30 | 84.70 |
| gpqa | 80.9% | 79.1% |
| hle | 11.9% | 11.1% |
| ifbench | 55.4% | 45.9% |
| lcr | 66.3% | 50.3% |
| livecodebench | 65.4% | 69.6% |
| math 500 | — | 99.2% |
| mmlu pro | 88.0% | 82.8% |
| scicode | 40.9% | 40.6% |
| tau2 | 71.4% | 90.4% |
| terminalbench hard | 34.3% | 17.4% |
Benchmark data from Artificial Analysis.