← All comparisons
LFM2 8B A1B vs Granite 4.0 H 1B
Liquid AI vs IBM — side-by-side benchmark comparison
| LFM2 8B A1B | Granite 4.0 H 1B | |
|---|---|---|
| Intelligence Index | 7.0 | 8.0 |
| Coding Index | 2.3 | 2.7 |
| Math Index | 25.3 | 6.3 |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.00 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | — |
| aime 25 | 25.3% | 6.3% |
| artificial analysis coding index | 2.30 | 2.70 |
| artificial analysis intelligence index | 7.00 | 8.00 |
| artificial analysis math index | 25.30 | 6.30 |
| gpqa | 34.4% | 26.3% |
| hle | 4.9% | 5.0% |
| ifbench | 26.3% | 26.2% |
| lcr | 0.0% | 6.3% |
| livecodebench | 15.1% | 11.5% |
| math 500 | — | — |
| mmlu pro | 50.5% | 27.7% |
| scicode | 6.8% | 8.2% |
| tau2 | 10.5% | 19.6% |
| terminalbench hard | 0.0% | 0.0% |
Benchmark data from Artificial Analysis.