NVIDIANemotron 3 Super
Best configuration ranks #219 of 610 on the BenchLeader Index at 53.6 ±5.1. Last measured 2 Sept 2026. Released 11 Mar 2026.
- Blended price
- $0.350/M
- $0.200 in · $0.800 out
- Output speed
- 96 tok/s
- First answer
- 25 s
- first token 0.53 s
- Context
- 262k
- Overall index54
- Reasoning54
- Coding54
- Agents & tools59
- Knowledge44
- Instruction following70
- Human preference54
- Long context59
- Composite46
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 |
|---|---|---|
| LMArena Hard Prompts | 1380#166 | LMArena |
| GPQA Diamond (AA)not in index | 80.0%#188 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 20.8%#157 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1409#167 | LMArena |
| SciCode (AA)not in index | 36.2%#133 | Artificial Analysis |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 28.8%#115 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 67.8%#158 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -41.5#259 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 71.5%#54 | Artificial Analysis |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1361#168 | LMArena |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 65.7%#188 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 13.6#242 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| DeepInfra | 42 tok/s | 0.53 s | $0.085 | $0.400 | 262k | bf16 |
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
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 | – | 28.5 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0029 | – | 31.6 s |
| Code edit | 6,000 / 1,500 | $0.0024 | – | 40.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.015 | – | 1.1 min |
| Structured extraction | 2,000 / 200 | $0.0006 | – | 27.4 s |
See also
Data as of 9 Sept 2026. Compare with another model.