← All comparisons
Llama Nemotron Super 49B v1.5 (Reasoning) vs Jamba 1.7 Large
NVIDIA vs AI21 Labs — side-by-side benchmark comparison
| Llama Nemotron Super 49B v1.5 (Reasoning) | Jamba 1.7 Large | |
|---|---|---|
| Intelligence Index | 18.7 | 10.9 |
| Coding Index | 15.1 | 7.8 |
| Math Index | 76.7 | 2.3 |
| Output speed (tok/s) | 48.1 | 56.9 |
| Blended price ($/1M) | $0.17 | $3.50 |
| Time to first token (s) | 0.30s | 0.90s |
| aime | 86.0% | 5.7% |
| aime 25 | 76.7% | 2.3% |
| artificial analysis coding index | 15.10 | 7.80 |
| artificial analysis intelligence index | 18.70 | 10.90 |
| artificial analysis math index | 76.70 | 2.30 |
| gpqa | 74.8% | 39.0% |
| hle | 6.8% | 3.8% |
| ifbench | 37.0% | 35.2% |
| lcr | 34.0% | 17.3% |
| livecodebench | 73.7% | 18.1% |
| math 500 | 98.3% | 60.0% |
| mmlu pro | 81.4% | 57.7% |
| scicode | 34.8% | 18.8% |
| tau2 | 28.1% | 13.5% |
| terminalbench hard | 5.3% | 2.3% |
Benchmark data from Artificial Analysis.