# V* leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/multimodal-grounded-v-star

Every model the catalog carries a published V* value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Vision-centric reasoning benchmark |
| Tasks | Frontier multimodal reasoning tasks |
| Difficulty | Frontier multimodal |
| Published by | [GLM-5V-Turbo](https://docs.z.ai/guides/vlm/glm-5v-turbo) |

A vision-centric benchmark for high-level multimodal reasoning and perception quality.

## V* ranking

14 models with a published V* value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Vision-centric reasoning benchmark | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K2.6](https://modelchoice.dev/models/kimi-2-6) | Moonshot AI | 96.9 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 96.9 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 95.8 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Step 3.7 Flash](https://modelchoice.dev/models/step-3-7-flash) | StepFun | 95.3 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 94.7 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.5-27B](https://modelchoice.dev/models/qwen3-5-27b) | Alibaba | 93.7 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen3.5-122B-A10B](https://modelchoice.dev/models/qwen3-5-122b-a10b) | Alibaba | 93.2 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Qwen3.5-35B-A3B](https://modelchoice.dev/models/qwen3-5-35b-a3b) | Alibaba | 92.7 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemini 3 Pro](https://modelchoice.dev/models/gemini-3-pro) | Google | 88.0 | Observed 2026-11-21 · source benchlm:models |
| 10 | [LFM3-VL-2B](https://modelchoice.dev/models/lfm3-vl-2b) | LiquidAI | 86.4 | Observed 2026-11-21 · source benchlm:models |
| 11 | [Nemotron 3.5 Super VL 120B A12B NVFP4](https://modelchoice.dev/models/nemotron-3-5-super-vl-120b-a12b-nvfp4) | NVIDIA | 86.0 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Nemotron 3.5 Super VL 120B A12B](https://modelchoice.dev/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | 85.6 | Observed 2026-11-21 · source benchlm:models |
| 13 | [GPT-5.2](https://modelchoice.dev/models/gpt-5-2) | OpenAI | 75.9 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 67.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
