← All comparisons
Apertus 70B Instruct vs Grok 4.20 0309 (Reasoning)
Swiss AI Initiative vs xAI — side-by-side benchmark comparison
| Apertus 70B Instruct | Grok 4.20 0309 (Reasoning) | |
|---|---|---|
| Intelligence Index | 7.7 | 48.5 |
| Coding Index | 1.9 | 42.2 |
| Math Index | — | — |
| Output speed (tok/s) | 0.0 | 217.8 |
| Blended price ($/1M) | $1.34 | $3.00 |
| Time to first token (s) | 0.00s | 13.18s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 1.90 | 42.20 |
| artificial analysis intelligence index | 7.70 | 48.50 |
| artificial analysis math index | — | — |
| gpqa | 27.2% | 88.5% |
| hle | 5.5% | 30.0% |
| ifbench | 25.9% | 82.9% |
| lcr | 0.0% | 59.0% |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 5.7% | 44.7% |
| tau2 | 12.9% | 96.5% |
| terminalbench hard | 0.0% | 40.9% |
Benchmark data from Artificial Analysis.