← All benchmarks
Llama Nemotron Super 49B v1.5 (Non-reasoning)
NVIDIA · Released 2025-07-25 · Independent benchmark scores from Artificial Analysis
Intelligence Index
7.4
Output speed
51.1
tokens/sec
Blended price
$0.40
per 1M tokens
Time to first token
4.34s
Model metadata
| Model ID | 26c0b5df-efa7-470f-a65e-2d883329e493 |
|---|---|
| Slug | llama-nemotron-super-49b-v1-5 |
| Release date | 2025-07-25 |
| Provider | NVIDIA |
| Provider slug | nvidia |
| Output speed | 51.1 tok/s |
| Time to first token | 4.34s |
| Time to first answer | 4.34s |
| Blended price ($/1M) | $0.40 |
| Input price ($/1M) | $0.40 |
| Output price ($/1M) | $0.40 |
All evaluation scores (17)
| aime | 13.7% |
|---|---|
| aime 25 | 8.0% |
| artificial analysis coding index | — |
| artificial analysis intelligence index | 7.40 |
| artificial analysis math index | 8.00 |
| gpqa | 48.1% |
| hle | 4.3% |
| ifbench | 32.9% |
| lcr | 24.7% |
| livecodebench | 29.0% |
| math 500 | 77.0% |
| mmlu pro | 69.2% |
| scicode | — |
| tau banking | — |
| tau2 | 25.1% |
| terminalbench hard | 3.8% |
| terminalbench v2 1 | — |
Source: artificialanalysis.ai/models/llama-nemotron-super-49b-v1-5
Benchmark data from Artificial Analysis.