← All comparisons
Granite 4.0 Micro vs Claude 4.1 Opus (Non-reasoning)
IBM vs Anthropic — side-by-side benchmark comparison
| Granite 4.0 Micro | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 7.7 | 36.0 |
| Coding Index | 5.0 | — |
| Math Index | 6.0 | — |
| Output speed (tok/s) | 0.0 | 44.7 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 0.00s | 1.63s |
| aime | — | — |
| aime 25 | 6.0% | — |
| artificial analysis coding index | 5.00 | — |
| artificial analysis intelligence index | 7.70 | 36.00 |
| artificial analysis math index | 6.00 | — |
| gpqa | 33.6% | — |
| hle | 5.1% | — |
| ifbench | 24.8% | — |
| lcr | 4.0% | — |
| livecodebench | 18.0% | — |
| math 500 | — | — |
| mmlu pro | 44.7% | — |
| scicode | 11.9% | — |
| tau2 | 12.6% | — |
| terminalbench hard | 1.5% | — |
Benchmark data from Artificial Analysis.