← All comparisons
Granite 4.1 30B vs Qwen3.5 122B A10B (Reasoning)
IBM vs Alibaba — side-by-side benchmark comparison
| Granite 4.1 30B | Qwen3.5 122B A10B (Reasoning) | |
|---|---|---|
| Intelligence Index | 14.7 | 41.6 |
| Coding Index | 10.1 | 34.7 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 146.7 |
| Blended price ($/1M) | $0.00 | $1.10 |
| Time to first token (s) | 0.00s | 1.05s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 10.10 | 34.70 |
| artificial analysis intelligence index | 14.70 | 41.60 |
| artificial analysis math index | — | — |
| gpqa | 48.1% | 85.7% |
| hle | 4.2% | 23.4% |
| ifbench | 44.4% | 75.7% |
| lcr | 18.7% | 66.7% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 25.8% | 42.0% |
| tau2 | 42.1% | 93.6% |
| terminalbench hard | 2.3% | 31.1% |
Benchmark data from Artificial Analysis.