NV Chat Benchmark
Nemotron 3.5 Super VL 52.7 leads since Oct 2026 In use Models answer chat prompts from an internal NVIDIA set. The Nemotron 3.5 Super VL card labels the score an LMArena v3 proxy.
The technical report calls it an internal chat benchmark developed at NVIDIA and gives no method details. The scoring type is a guess.
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
Nemotron 3.5 Super VL leads with 52.7
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Nemotron 3.5 Super VL 52.7
- 2 Nemotron 3.5 Lightning 30B-A3B 12.1
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Nemotron 3.5 Super VL | 52.7 | Oct 2026 | Model card | |
| 2 | Nemotron 3.5 Lightning 30B-A3B | 12.1 | Oct 2026 | Model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 15 Oct 2026 | Nemotron 3.5 Super VL | 52.7 | LMArena v3 proxy (NV Chat Benchmark in the technical report) |
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 15 Oct 2026 | Nemotron 3.5 Super VL technical report | 52.7 | NV Chat Benchmark, win rate judged by Gemini 3.1 Pro (Table 10) | Capabilities |
| 15 Oct 2026 | Nemotron 3.5 Lightning 30B-A3B technical report | 12.1 | LM Arena Proxy, BF16 acc. (Table 22), the row Table 23 calls NV Chat Benchmark | Capabilities |
More in Instructions and chat
- IFEval In use Models answer about 500 prompts containing verifiable instructions such as word limits or required keywords. Code checks each instruction for strict and loose accuracy.
Gemma 4 31B IT 98.9% - IFBench In use 58 new out-of-domain verifiable output constraints. Scored by programmatic constraint checks (strict or loose). Nemotron-Cascade 2 30B-A3B 82.9%
- MultiChallenge In use Multi-turn conversations testing instruction retention, inference memory, versioned editing and self-coherence. Graded by LLM judge with rubrics. GPT-6.1 Sol 82%
- Multi-IF In use Models follow verifiable instructions over three-turn conversations in eight languages, extending IFEval. Scored by instruction accuracy at each turn. LFM3-1.7B 89.1%
- AdvancedIF In use Models respond to over 1,600 prompts with complex, multi-turn, and system-level instructions. A judge model checks each response against expert-written rubrics.
MAI-Thinking-1 85% - IFStruct In use Models generate JSON or YAML that must follow a requested schema and phrasing constraints, without constrained decoding. A response passes only if every structural constraint holds. LFM3-1.7B 93.7%