Back to models
Intelligence Index
Reasoning setting
26.5#37 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.10 in / $0.40 out / 1M tokOpenRouter · DeepInfra · FP4
- Context window
- 1M tok
Performance profile
CodingRank #40 of 94
47.8%
SciCodeCost efficiencyRank #21 of 67
140.7pts / $
Intelligence ÷ eval costCapabilities
Context window
Modalities
Measured setting
Integration
Reasoning trade-offs
Source (opens in a new tab)Nemotron 3.5 Super VL
Cost per task (USD) · log scale
Nemotron 3.5 Super VLReasoning
- Intelligence Index
- 26.5
- Cost / task
- $0.1882
- Evaluation time
- 1.9m
Pricing & access
USD per 1M tokens
- Input
- $0.15
- Output
- $0.50
- Cached input
- $0.02
Run locally
- Original download
- 248.9 GB
- App memory
- Unverified
- Documented software
- vLLMSetup guide (opens in a new tab)
Find GGUF downloadsBenchmarks
Full leaderboardSource (opens in a new tab)30.7%, rank 49 of 12647.8%, rank 40 of 940.0%, rank 56 of 8769.0%, rank 70 of 1251,162 Elo, rank 40 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 46Inkling SmallReasoning33.3%
- 47K2 Horizon 375B A23BReasoning32.0%
- 48InklingExtra high31.9%
- 49Nemotron 3.5 Super VLReasoning30.7%
- 50A.X-K2Reasoning29.6%
- 51Solar Pro 4Reasoning29.2%
- 52Qwen3.5 397B A17BReasoning29.0%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherQuasar 438BMax
- Intelligence Index
- 26.7+0.2
- Cost / task
- $2.02+976%
- Higher score, lower costGPT-6 LunaMax
- Intelligence Index
- 38.1+11.6
- Cost / task
- $0.068−64%
- More from NVIDIANemotron 3 Ultra 550B A55BReasoning
- Intelligence Index
- 22.9−3.6
- Cost / task
- $0.577+207%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.