← All comparisons
Granite 4.0 H Small vs Claude 4.1 Opus (Non-reasoning)
IBM vs Anthropic — side-by-side benchmark comparison
| Granite 4.0 H Small | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 10.8 | 36.0 |
| Coding Index | 8.5 | — |
| Math Index | 13.7 | — |
| Output speed (tok/s) | 401.2 | 44.7 |
| Blended price ($/1M) | $0.11 | $32.81 |
| Time to first token (s) | 8.75s | 1.63s |
| aime | — | — |
| aime 25 | 13.7% | — |
| artificial analysis coding index | 8.50 | — |
| artificial analysis intelligence index | 10.80 | 36.00 |
| artificial analysis math index | 13.70 | — |
| gpqa | 41.6% | — |
| hle | 3.7% | — |
| ifbench | 31.5% | — |
| lcr | 9.0% | — |
| livecodebench | 25.1% | — |
| math 500 | — | — |
| mmlu pro | 62.4% | — |
| scicode | 20.9% | — |
| tau2 | 17.3% | — |
| terminalbench hard | 2.3% | — |
Benchmark data from Artificial Analysis.