← All comparisons
Kimi K2.6 vs Llama 3.3 Nemotron Super 49B v1 (Reasoning)
Kimi vs NVIDIA — side-by-side benchmark comparison
| Kimi K2.6 | Llama 3.3 Nemotron Super 49B v1 (Reasoning) | |
|---|---|---|
| Intelligence Index | 53.9 | 18.5 |
| Coding Index | 47.1 | 9.4 |
| Math Index | — | 54.7 |
| Output speed (tok/s) | 42.0 | 0.0 |
| Blended price ($/1M) | $1.71 | $0.00 |
| Time to first token (s) | 1.30s | 0.00s |
| aime | — | 58.3% |
| aime 25 | — | 54.7% |
| artificial analysis coding index | 47.10 | 9.40 |
| artificial analysis intelligence index | 53.90 | 18.50 |
| artificial analysis math index | — | 54.70 |
| gpqa | 91.1% | 64.3% |
| hle | 35.9% | 6.5% |
| ifbench | 76.0% | 38.1% |
| lcr | 69.7% | 17.0% |
| livecodebench | — | 27.7% |
| math 500 | — | 95.9% |
| mmlu pro | — | 78.5% |
| scicode | 53.5% | 28.2% |
| tau2 | 95.9% | 26.9% |
| terminalbench hard | 43.9% | 0.0% |
Benchmark data from Artificial Analysis.