← All comparisons
GPT-5.4 (xhigh) vs Claude 4.1 Opus (Non-reasoning)
OpenAI vs Anthropic — side-by-side benchmark comparison
| GPT-5.4 (xhigh) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 56.8 | 36.0 |
| Coding Index | 57.2 | — |
| Math Index | — | — |
| Output speed (tok/s) | 88.5 | 44.7 |
| Blended price ($/1M) | $5.63 | $32.81 |
| Time to first token (s) | 161.08s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 57.20 | — |
| artificial analysis intelligence index | 56.80 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 92.0% | — |
| hle | 41.6% | — |
| ifbench | 73.9% | — |
| lcr | 74.0% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 56.6% | — |
| tau2 | 87.1% | — |
| terminalbench hard | 57.6% | — |
Benchmark data from Artificial Analysis.