← All comparisons
Motif-2-12.7B-Reasoning vs Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)
Motif Technologies vs Google — side-by-side benchmark comparison
| Motif-2-12.7B-Reasoning | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 19.1 | 25.7 |
| Coding Index | 11.9 | 22.1 |
| Math Index | 80.3 | 56.7 |
| 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 | 80.3% | 56.7% |
| artificial analysis coding index | 11.90 | 22.10 |
| artificial analysis intelligence index | 19.10 | 25.70 |
| artificial analysis math index | 80.30 | 56.70 |
| gpqa | 69.5% | 76.6% |
| hle | 8.2% | 7.8% |
| ifbench | 57.0% | 43.5% |
| lcr | 13.0% | 56.7% |
| livecodebench | 65.1% | 62.5% |
| math 500 | — | — |
| mmlu pro | 79.6% | 83.6% |
| scicode | 28.2% | 37.5% |
| tau2 | 46.5% | 28.4% |
| terminalbench hard | 3.8% | 14.4% |
Benchmark data from Artificial Analysis.