Benchmark
V* Benchmark
What is V*?
A visual reasoning benchmark evaluating multimodal inference under challenging spatial and grounded tasks. Benchmark Radar tracks 7 reported scores for V*…
- Released
- 2023-12-21
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 7
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/v-star?top_n=500
V* results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5V-Turbo | Z.ai | 0.89 | 2026-04-02 | evidence |
| Kimi K2.6 | Moonshot AI | 0.969 | 2026-04-20 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.932 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.937 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.927 | 2026-02-24 | evidence |
| Qwen3.6 Plus | Qwen | 0.969 | 2026-04-02 | evidence |
| Qwen3.6-27B | Qwen | 0.947 | 2026-04-21 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.