NVIDIALlama Nemotron Super 49B v1.5
Best configuration ranks #458 of 610 on the BenchLeader Index at 42.6 ±1.8. Released 25 Jul 2025.
- Blended price
- $0.400/M
- $0.400 in · $0.400 out
- Output speed
- 35 tok/s
- First answer
- 12 s
- first token 12 s
- Context
- 128k
- Overall index43
- Agents & tools37
- Knowledge42
- Instruction following36
- Long context38
- Composite38
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| GPQA Diamond (AA)not in index | 48.1%#415 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.3%#429 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 3.8%#283 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 25.1%#283 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -46.2#289 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 32.9%#320 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 24.7%#341 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 7.4#401 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0003 | – | 20.4 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0050 | – | 28.9 s |
| Code edit | 6,000 / 1,500 | $0.0030 | – | 54.7 s |
| Agentic coding session | 60,000 / 4,000 | $0.026 | – | 2.1 min |
| Structured extraction | 2,000 / 200 | $0.0009 | – | 17.5 s |
See also
Data as of 9 Sept 2026. Compare with another model.