MMBench EN-DEV v1.1
MMBench-EN-DEV v1.1 - multimodal benchmark English dev set.
Category
Vision & Language
Max Score
100.0
Score Type
percent
Active
Yes
Model Scores
Scores for MMBench EN-DEV v1.1
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.6-35B-A3B |
100.00%
|
16.04.2026 | Verified |
| Gemma4-31B-it |
68.33%
|
16.04.2026 | Unverified |
| Qwen3.5-35B-A3B |
78.33%
|
16.04.2026 | Unverified |
| Gemma4-26B-A4B |
36.67%
|
16.04.2026 | Unverified |
| Claude-Sonnet-4.5 |
25.00%
|
16.04.2026 | Unverified |
| Qwen3.6-27B |
91.67%
|
22.04.2026 | Verified |
| Qwen3.5-27B |
96.67%
|
16.04.2026 | Unverified |
| Qwen3.5-4B |
43.33%
|
01.02.2026 | Verified |
| Qwen3.5-122B-A10B |
100.00%
|
01.02.2026 | Verified |
| GPT-5-mini 2025-08-07 |
86.80
|
01.02.2026 | Unverified |
| Qwen3-235B-A22B |
48.33%
|
01.02.2026 | Unverified |
| Qwen3-VL-235B-A22B |
48.33%
|
01.02.2026 | Verified |