← All comparisons
Grok 4.3 (Non-reasoning) vs Granite 4.0 H 1B
xAI vs IBM — side-by-side benchmark comparison
| Grok 4.3 (Non-reasoning) | Granite 4.0 H 1B | |
|---|---|---|
| Intelligence Index | 31.0 | 8.0 |
| Coding Index | 25.1 | 2.7 |
| Math Index | — | 6.3 |
| Output speed (tok/s) | 143.7 | 0.0 |
| Blended price ($/1M) | $1.56 | $0.00 |
| Time to first token (s) | 0.42s | 0.00s |
| aime | — | — |
| aime 25 | — | 6.3% |
| artificial analysis coding index | 25.10 | 2.70 |
| artificial analysis intelligence index | 31.00 | 8.00 |
| artificial analysis math index | — | 6.30 |
| gpqa | 65.8% | 26.3% |
| hle | 6.5% | 5.0% |
| ifbench | 47.6% | 26.2% |
| lcr | 24.7% | 6.3% |
| livecodebench | — | 11.5% |
| math 500 | — | — |
| mmlu pro | — | 27.7% |
| scicode | 37.4% | 8.2% |
| tau2 | 65.8% | 19.6% |
| terminalbench hard | 18.9% | 0.0% |
Benchmark data from Artificial Analysis.