Multimodal · Benchmark profile
A vision-centric benchmark for high-level multimodal reasoning and perception quality.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on V*
Kimi K2.6 leads at 96.9%, followed by Qwen3.6 Plus (96.9%) and Qwen3.5 397B (95.8%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
11 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Kimi K2.6 | #1 | Moonshot AI | 96.9% |
| Qwen3.6 Plus | #2 | Alibaba Cloud | 96.9% |
| Qwen3.5 397B | #3 | Alibaba Cloud | 95.8% |
| Step 3.7 Flash | #4 | StepFun | 95.3% |
| Qwen3.6 27B | #5 | Alibaba Cloud | 94.7% |
| Qwen3.5 27B | #6 | Alibaba Cloud | 93.7% |
| Qwen3.5-122B-A10B | #7 | Alibaba Cloud | 93.2% |
| Qwen3.5-35B-A3B | #8 | Alibaba Cloud | 92.7% |
| Gemini 3 Pro | #9 | 88% | |
| GPT-5.2 | #10 | OpenAI | 75.9% |
| Claude Opus 4.5 | #11 | Anthropic | 67% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Kimi K2.6 kimi-k2.6 | Moonshot AI | open | Estimated reference | 96.9% |
| #2 | Qwen3.6 Plus qwen3-6-plus | Alibaba Cloud | closed | Reference only | 96.9% |
| #3 | Qwen3.5 397B qwen3.5-397b-a17b | Alibaba Cloud | open | Estimated reference | 95.8% |
| #4 | Step 3.7 Flash step-3-7-flash | StepFun | open | Estimated reference | 95.3% |
| #5 | Qwen3.6 27B qwen3.6-27b | Alibaba Cloud | open | Estimated reference | 94.7% |
| #6 | Qwen3.5 27B qwen3.5-27b | Alibaba Cloud | open | Reference only | 93.7% |
| #7 | Qwen3.5-122B-A10B qwen3-5-122b-a10b | Alibaba Cloud | open | Reference only | 93.2% |
| #8 | Qwen3.5-35B-A3B qwen3-5-35b-a3b | Alibaba Cloud | open | Reference only | 92.7% |
| #9 | Gemini 3 Pro gemini-3-pro | closed | Reference only | 88% | |
| #10 | GPT-5.2 gpt-5.2 | OpenAI | closed | Estimated reference | 75.9% |
| #11 | Claude Opus 4.5 claude-opus-4-5 | Anthropic | closed | Reference only | 67% |
The top of this snapshot is led by Kimi K2.6 at 96.9%; third place is 1.1 points behind. The top-10 spread is 21.0 points.
About V*
A vision-centric benchmark for high-level multimodal reasoning and perception quality. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A vision-centric benchmark for high-level multimodal reasoning and perception quality.
Kimi K2.6 by Moonshot AI currently leads with 96.9%.
11 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
