← All comparisons
Grok 4.3 (Non-reasoning) vs Claude 4.1 Opus (Non-reasoning)
xAI vs Anthropic — side-by-side benchmark comparison
| Grok 4.3 (Non-reasoning) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 31.0 | 36.0 |
| Coding Index | 25.1 | — |
| Math Index | — | — |
| Output speed (tok/s) | 143.7 | 44.7 |
| Blended price ($/1M) | $1.56 | $32.81 |
| Time to first token (s) | 0.42s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 25.10 | — |
| artificial analysis intelligence index | 31.00 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 65.8% | — |
| hle | 6.5% | — |
| ifbench | 47.6% | — |
| lcr | 24.7% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 37.4% | — |
| tau2 | 65.8% | — |
| terminalbench hard | 18.9% | — |
Benchmark data from Artificial Analysis.