← All comparisons
K2-V2 (medium) vs Claude 4.1 Opus (Non-reasoning)
MBZUAI Institute of Foundation Models vs Anthropic — side-by-side benchmark comparison
| K2-V2 (medium) | Claude 4.1 Opus (Non-reasoning) | |
|---|---|---|
| Intelligence Index | 18.7 | 36.0 |
| Coding Index | 14.0 | — |
| Math Index | 64.7 | — |
| 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 | — | — |
| aime 25 | 64.7% | — |
| artificial analysis coding index | 14.00 | — |
| artificial analysis intelligence index | 18.70 | 36.00 |
| artificial analysis math index | 64.70 | — |
| gpqa | 59.8% | — |
| hle | 4.4% | — |
| ifbench | 55.1% | — |
| lcr | 28.0% | — |
| livecodebench | 54.1% | — |
| math 500 | — | — |
| mmlu pro | 76.1% | — |
| scicode | 25.2% | — |
| tau2 | 24.9% | — |
| terminalbench hard | 8.3% | — |
Benchmark data from Artificial Analysis.