← All comparisons
Gemma 4 26B A4B (Non-reasoning) vs Claude 4.1 Opus (Non-reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemma 4 26B A4B (Non-reasoning) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 27.1 | 36.0 |
| Coding Index | 29.1 | — |
| Math Index | — | — |
| Output speed (tok/s) | 71.1 | 44.7 |
| Blended price ($/1M) | $0.20 | $32.81 |
| Time to first token (s) | 0.80s | 1.63s |
| aime | — | — |
| aime 25 | — | — |
| artificial analysis coding index | 29.10 | — |
| artificial analysis intelligence index | 27.10 | 36.00 |
| artificial analysis math index | — | — |
| gpqa | 71.4% | — |
| hle | 10.7% | — |
| ifbench | 45.4% | — |
| lcr | 39.7% | — |
| livecodebench | — | — |
| math 500 | — | — |
| mmlu pro | — | — |
| scicode | 37.3% | — |
| tau2 | 40.4% | — |
| terminalbench hard | 25.0% | — |
Benchmark data from Artificial Analysis.