Kimi-VL-A3B-Thinking
Kimi-VL-A3B-Thinking.
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Moonshot AI Apr 2025
Kimi-VL-A3B-Thinking
Open weights Small
No Epoch Capabilities Index score yet
- MATH-Vision (MathVision) 36.8% #40 /42
- MathVista 71.3% #38 /64
- MMBench-EN v1.1 72.5% #101 /178
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 64.1% | #130 of 178 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMStar | 60.8% | #56 of 173 | Official leaderboard | |
| MMBench-EN v1.1 | 72.5% | #101 of 178 | Official leaderboard | |
| MathVista | 71.3% | #38 of 64 | Model card | |
| MMMU | 61.7% | #79 of 97 | Model card | |
| MATH-Vision (MathVision) | 36.8% | #40 of 42 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 65.9 | #53 of 173 | Official leaderboard |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it.
Kimi-VL Technical Report 10 Apr 2025
Capabilities
- MATH-Vision (MathVision) 36.8
- MathVista 71.3
- MMMU 61.7