mirror of
https://www.modelscope.cn/moonshotai/Kimi-VL-A3B-Thinking-2506.git
synced 2026-04-02 19:13:01 +08:00
Update README.md
This commit is contained in:
@ -97,6 +97,14 @@ Comparison with 30B-70B open-source models:
|
||||
| MMLongBench-DOC (Acc) | 42.1 | - | 38.8 | - |
|
||||
</div>
|
||||
|
||||
Text results, comparison with 30B-level non-thinking VLMs:
|
||||
|
||||
| Benchmark (Metric) | Kimi-VL-A3B-Thinking-2506 | Qwen2.5-VL-32B | Gemma3-27B-IT |
|
||||
|----------------------------|---------------------------|---------------|---------------|
|
||||
| MMLU | **82.0** | 78.4 | 76.9 |
|
||||
| MMLU-Pro | 68.5 | **68.8** | 67.5 |
|
||||
| MATH | **91.8** | 82.2 | 89.0 |
|
||||
| GPQA-Diamond | 42.3 | **46.0** | **46.0** |
|
||||
|
||||
## 3. Usage
|
||||
|
||||
|
||||
Reference in New Issue
Block a user