← All benchmarks
Llama Nemotron Super 49B v1.5 (Reasoning)
NVIDIA · Released 2025-07-25 · Independent benchmark scores from Artificial Analysis
Intelligence Index
9.0
Output speed
58.7
tokens/sec
Blended price
$0.40
per 1M tokens
Time to first token
9.38s
Model metadata
| Model ID | e1cfa926-9e2b-4a0d-8c31-48366a5041c5 |
|---|---|
| Slug | llama-nemotron-super-49b-v1-5-reasoning |
| Release date | 2025-07-25 |
| Provider | NVIDIA |
| Provider slug | nvidia |
| Output speed | 58.7 tok/s |
| Time to first token | 9.38s |
| Time to first answer | 43.44s |
| Blended price ($/1M) | $0.40 |
| Input price ($/1M) | $0.40 |
| Output price ($/1M) | $0.40 |
All evaluation scores (17)
| aime | 86.0% |
|---|---|
| aime 25 | 76.7% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 9.00 |
| artificial analysis math index | 76.70 |
| gpqa | 74.8% |
| hle | 7.3% |
| ifbench | 37.0% |
| lcr | — |
| livecodebench | 73.7% |
| math 500 | 98.3% |
| mmlu pro | 81.4% |
| scicode | — |
| tau banking | — |
| tau2 | 28.1% |
| terminalbench hard | 5.3% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/llama-nemotron-super-49b-v1-5-reasoning
Benchmark data from Artificial Analysis.