Nemotron 3.5 Super VLopen
NVIDIA
32.3#333 of 427 overall
- Input / output
- US$ 0,15 / US$ 0,50 US$ per 1M tokens
- Context
- 1.0M tokens
- Release
- 10/15/2026 release date
- Speed
- 410 tok/s first token in 0.56 s
Scores by source
Scores by sourcepercentile = % of ranked models it beats| Metric | Value | Percentile | Source |
|---|---|---|---|
| LiveBench weight 3 | 50.2 | 13% | LiveBench |
| AA Intelligence Index weight 3 | 13.6 | 23% | Artificial Analysis |
| Arena text (Elo) weight 2 | 1405 | 47% | LMArena |
| Arena WebDev (Elo) weight 1 | 1399 | 33% | LMArena |
| Arena vision (Elo) weight 0.5 | 1205 | 31% | LMArena |
| Humanity's Last Exam weight 1 | 30.7 | 80% | Artificial Analysis |
| Terminal-Bench weight 1 | 0.0 | 22% | Artificial Analysis |
| Long-context reasoning | 69.0 | 59% | Artificial Analysis |
| LiveBench long agentic | 11.7 | 18% | LiveBench |
| LiveBench reasoning | 74.6 | 10% | LiveBench |
| LiveBench coding | 71.3 | 19% | LiveBench |
| LiveBench browser | 21.6 | 16% | LiveBench |
| LiveBench data analysis | 64.6 | 19% | LiveBench |
| LiveBench research | 66.7 | 19% | LiveBench |
| LiveBench design | 62.8 | 16% | LiveBench |
By category
| Category | Score | Rank | Metrics |
|---|---|---|---|
| Agentic | 29.9 | #144 | LiveBench long agentic, Terminal-Bench |
| Coding | 34.1 | #96 | LiveBench coding, Arena WebDev (Elo) |
| Reasoning | 46.7 | #242 | LiveBench reasoning, Humanity's Last Exam |
| Data analysis | 34.7 | #26 | LiveBench data analysis |
| Research | 42.8 | #228 | LiveBench research, Long-context reasoning |
| Design | 33.0 | #97 | LiveBench design, Arena WebDev (Elo) |
| Browser use | 33.0 | #27 | LiveBench browser |
| Chat | 48.5 | #105 | Arena text (Elo) |
| Vision | 40.7 | #73 | Arena vision (Elo) |
History
RankingIA score on each collection day (hover to see the rank).
Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.