← All comparisons
Gemma 3 27B Instruct vs Claude 4.1 Opus (Reasoning)
Google vs Anthropic — side-by-side benchmark comparison
| Gemma 3 27B Instruct | Claude 4.1 Opus (Reasoning) | |
|---|---|---|
| Intelligence Index | 10.3 | 42.0 |
| Coding Index | 9.6 | 36.5 |
| Math Index | 20.7 | 80.3 |
| Output speed (tok/s) | 0.0 | 44.5 |
| Blended price ($/1M) | $0.14 | $32.81 |
| Time to first token (s) | 0.00s | 8.55s |
| aime | 25.3% | — |
| aime 25 | 20.7% | 80.3% |
| artificial analysis coding index | 9.60 | 36.50 |
| artificial analysis intelligence index | 10.30 | 42.00 |
| artificial analysis math index | 20.70 | 80.30 |
| gpqa | 42.8% | 80.9% |
| hle | 4.7% | 11.9% |
| ifbench | 31.8% | 55.4% |
| lcr | 5.7% | 66.3% |
| livecodebench | 13.7% | 65.4% |
| math 500 | 88.3% | — |
| mmlu pro | 66.9% | 88.0% |
| scicode | 21.2% | 40.9% |
| tau2 | 10.5% | 71.4% |
| terminalbench hard | 3.8% | 34.3% |
Benchmark data from Artificial Analysis.