← All comparisons
Gemma 3 1B Instruct vs Claude 4.1 Opus (Non-reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemma 3 1B Instruct | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 5.6 | 36.0 |
| Coding Index | 0.2 | — |
| Math Index | 3.3 | — |
| Output speed (tok/s) | 0.0 | 44.7 |
| Blended price ($/1M) | $0.00 | $32.81 |
| Time to first token (s) | 0.00s | 1.63s |
| aime | 0.0% | — |
| aime 25 | 3.3% | — |
| artificial analysis coding index | 20.0% | — |
| artificial analysis intelligence index | 5.60 | 36.00 |
| artificial analysis math index | 3.30 | — |
| gpqa | 23.7% | — |
| hle | 5.2% | — |
| ifbench | 19.9% | — |
| lcr | 0.0% | — |
| livecodebench | 1.7% | — |
| math 500 | 48.4% | — |
| mmlu pro | 13.5% | — |
| scicode | 0.7% | — |
| tau2 | 10.5% | — |
| terminalbench hard | 0.0% | — |
Benchmark data from Artificial Analysis.