← All comparisons
Granite 4.0 H 350M vs Qwen3.5 122B A10B (Non-reasoning)
IBM vs Alibaba — side-by-side benchmark comparison
| Granite 4.0 H 350M | Qwen3.5 122B A10B (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 5.4 | 35.9 |
| Coding Index | 0.6 | 31.6 |
| Math Index | 1.3 | — |
| Output speed (tok/s) | 0.0 | 165.9 |
| Blended price ($/1M) | $0.00 | $1.10 |
| Time to first token (s) | 0.00s | 1.06s |
| aime | — | — |
| aime 25 | 1.3% | — |
| artificial analysis coding index | 60.0% | 31.60 |
| artificial analysis intelligence index | 5.40 | 35.90 |
| artificial analysis math index | 1.30 | — |
| gpqa | 25.7% | 82.7% |
| hle | 6.4% | 14.8% |
| ifbench | 17.6% | 50.8% |
| lcr | 0.0% | 56.0% |
| livecodebench | 1.9% | — |
| math 500 | — | — |
| mmlu pro | 12.7% | — |
| scicode | 1.7% | 35.6% |
| tau2 | 14.6% | 84.5% |
| terminalbench hard | 0.0% | 29.5% |
Benchmark data from Artificial Analysis.