Codesota · Models · Kimi-VL-A3B-Instruct5 results · 5 benchmarks
Model card
Kimi-VL-A3B-Instruct.
unknown
§ 02 · Benchmarks
Every benchmark Kimi-VL-A3B-Instruct has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | MMStar | Multimodal · Image-Text-to-Text | accuracy | 61.3% | #19 | — | source ↗ |
| 02 | RealWorldQA | Multimodal · Visual Question Answering | accuracy | 68.1% | #19 | — | source ↗ |
| 03 | Video-MME | Multimodal · Video Understanding | accuracy | 67.8% | #20 | — | source ↗ |
| 04 | MMMU | Multimodal · Image-Text-to-Text | accuracy | 57.0% | #26 | — | source ↗ |
| 05 | OSWorld | Agentic AI · Web & Desktop Agents | success-rate | 8.2% | #27 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area
Where Kimi-VL-A3B-Instruct actually performs.
§ 04 · Papers
1 paper with results for Kimi-VL-A3B-Instruct.
- 2025-04-10· 5 results
Kimi-VL Technical Report
§ 06 · Sources & freshness
Where these numbers come from.
pwc-dump
5
results
0 of 5 rows marked verified.