← All comparisons
Apertus 8B Instruct vs Gemini 1.5 Flash (May '24)
Swiss AI Initiative vs Google — side-by-side benchmark comparison
| Apertus 8B Instruct | Gemini 1.5 Flash (May '24) | |
|---|---|---|
| Intelligence Index | 5.9 | 10.5 |
| Coding Index | 1.4 | — |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 0.0 |
| Blended price ($/1M) | $0.13 | $0.00 |
| Time to first token (s) | 0.00s | 0.00s |
| aime | — | 9.3% |
| aime 25 | — | — |
| artificial analysis coding index | 1.40 | — |
| artificial analysis intelligence index | 5.90 | 10.50 |
| artificial analysis math index | — | — |
| gpqa | 25.6% | 32.4% |
| hle | 5.0% | 4.2% |
| ifbench | 22.4% | — |
| lcr | 0.0% | — |
| livecodebench | — | 19.6% |
| math 500 | — | 55.4% |
| mmlu pro | — | 57.4% |
| scicode | 4.1% | 18.1% |
| tau2 | 11.4% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.