← All comparisons
Claude 4.1 Opus (Non-reasoning) vs Phi-3 Mini Instruct 3.8B
Anthropic vs Microsoft — side-by-side benchmark comparison
| Claude 4.1 Opus (Non-reasoning) | Phi-3 Mini Instruct 3.8B | |
|---|---|---|
| Intelligence Index | 36.0 | 10.1 |
| Coding Index | — | 3.0 |
| Math Index | — | 0.3 |
| Output speed (tok/s) | 44.7 | 0.0 |
| Blended price ($/1M) | $32.81 | $0.00 |
| Time to first token (s) | 1.63s | 0.00s |
| aime | — | 4.0% |
| aime 25 | — | 0.3% |
| artificial analysis coding index | — | 3.00 |
| artificial analysis intelligence index | 36.00 | 10.10 |
| artificial analysis math index | — | 30.0% |
| gpqa | — | 31.9% |
| hle | — | 4.4% |
| ifbench | — | 23.9% |
| lcr | — | 2.0% |
| livecodebench | — | 11.6% |
| math 500 | — | 45.7% |
| mmlu pro | — | 43.5% |
| scicode | — | 9.0% |
| tau2 | — | 0.0% |
| terminalbench hard | — | 0.0% |
Benchmark data from Artificial Analysis.