Kimi-VL-A3B-Thinking
Kimi-VL-A3B-Thinking.
10
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
- OCR-Reasoning 20.5% #10 /15
- CrossVid 28.2% #5 /13
- MM-Vet 67.4% #27 /164
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 | |
|---|---|---|---|---|
| MM-Vet | 67.4% | #27 of 164 | Official leaderboard | |
| MMStar | 60.8% | #56 of 173 | Official leaderboard | |
| CrossVid | 28.2% | #5 of 13 | Official leaderboard | |
| MMBench-EN v1.1 | 72.5% | #101 of 178 | Official leaderboard | |
| MathVista | 71.3% | #43 of 70 | Lab model card | |
| OCR-Reasoning | 20.5% | #10 of 15 | Official leaderboard | |
| MMMU | 61.7% | #84 of 103 | Lab model card | |
| MATH-Vision (MathVision) | 36.8% | #49 of 51 | Lab model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 65.9 | #53 of 173 | Official leaderboard |
Its lab's number next to a leaderboard
Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.
| Benchmark | Lab says | Board says | Gap |
|---|---|---|---|
| MATH-Vision (MathVision) | 36.8% MathVision (full) (Pass@1) | 36.8% Leaderboard | Same |
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 Apr 10, 2025
Capabilities
- MATH-Vision (MathVision) 36.8
- MathVista 71.3
- MMMU 61.7