← All comparisons
gpt-oss-120b (low) vs Motif-2-12.7B-Reasoning
OpenAI vs Motif Technologies — side-by-side benchmark comparison
| gpt-oss-120b (low) | Motif-2-12.7B-Reasoning | |
|---|---|---|
| Intelligence Index | 24.5 | 19.1 |
| Coding Index | 15.5 | 11.9 |
| Math Index | 66.7 | 80.3 |
| Output speed (tok/s) | 370.0 | 0.0 |
| Blended price ($/1M) | $0.26 | $0.00 |
| Time to first token (s) | 0.49s | 0.00s |
| aime | — | — |
| aime 25 | 66.7% | 80.3% |
| artificial analysis coding index | 15.50 | 11.90 |
| artificial analysis intelligence index | 24.50 | 19.10 |
| artificial analysis math index | 66.70 | 80.30 |
| gpqa | 67.2% | 69.5% |
| hle | 5.2% | 8.2% |
| ifbench | 58.3% | 57.0% |
| lcr | 43.7% | 13.0% |
| livecodebench | 70.7% | 65.1% |
| math 500 | — | — |
| mmlu pro | 77.5% | 79.6% |
| scicode | 36.0% | 28.2% |
| tau2 | 45.0% | 46.5% |
| terminalbench hard | 5.3% | 3.8% |
Benchmark data from Artificial Analysis.