Multimodal Reasoning on Multimodal Reasoning Aggregate 6 benchmarks
80.8Average ScoreM2Note
Evaluation Results
| Method | Links | |
|---|---|---|
| M2NoteBackbone=Qwen3-VL-Plus, Evolving Mode=Self-Evolving, Mem=28, Len=4622026.07 | 80.8 | |
| M2NoteBackbone=GPT-5.4, Evolving Mode=Self-Evolving, Mem=28, Len=4622026.07 | 79.6 | |
| VanillaBackbone=Qwen3-VL-Plus, Evolving Mode=Self-Evolving2026.07 | 79.5 | |
| VanillaBackbone=GPT-5.4, Evolving Mode=Self-Evolving2026.07 | 78.8 | |
| CoT+M2NoteBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving, Mem=32, Len=3152026.07 | 78.4 | |
| CoTBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving2026.07 | 77.6 | |
| M2NoteBackbone (Tuning)=Qwen3-VL-8B-Instruct, Backbone (Tuner)=Qwen3-VL-Plus, Evolving Mode=Cross-Model Evolving, Mem=43, Len=4452026.07 | 76.6 | |
| M2NoteBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving, Mem=50, Len=2612026.07 | 76.2 | |
| VanillaBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving2026.07 | 74.3 | |
| VanillaBackbone (Tuning)=Qwen3-VL-8B-Instruct, Backbone (Tuner)=Qwen3-VL-Plus, Evolving Mode=Cross-Model Evolving2026.07 | 74.3 | |
| Vision-ZeroEvolving Mode=Self-Evolving2026.07 | 72.65 |