List your company

STEM Puzzle on MathVista

83.9AccuracyCoT+M2Note
67.57271.81176.0580.289Jul 1, 2026

Evaluation results

MethodLinks
CoT+M2NoteBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving, Mem=32, Len=3152026.0783.9
CoTBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving2026.0782.9
M2NoteBackbone=Qwen3-VL-Plus, Evolving Mode=Self-Evolving, Mem=28, Len=4622026.0780.1
M2NoteBackbone (Tuning)=Qwen3-VL-8B-Instruct, Backbone (Tuner)=Qwen3-VL-Plus, Evolving Mode=Cross-Model Evolving, Mem=43, Len=4452026.0778.3
VanillaBackbone=Qwen3-VL-Plus, Evolving Mode=Self-Evolving2026.0778
M2NoteBackbone=GPT-5.4, Evolving Mode=Self-Evolving, Mem=28, Len=4622026.0778
M2NoteBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving, Mem=50, Len=2612026.0777.3
VanillaBackbone=GPT-5.4, Evolving Mode=Self-Evolving2026.0777.2
DPEBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving2026.0776.2
VanillaBackbone=Qwen3-VL-8B-Instruct, Evolving Mode=Self-Evolving2026.0773.2
VanillaBackbone (Tuning)=Qwen3-VL-8B-Instruct, Backbone (Tuner)=Qwen3-VL-Plus, Evolving Mode=Cross-Model Evolving2026.0773.2
Vision-ZeroEvolving Mode=Self-Evolving2026.0772.6
EvoLMMEvolving Mode=Self-Evolving2026.0770.5
iReasonerEvolving Mode=Self-Evolving2026.0769.7
VisPlayEvolving Mode=Self-Evolving2026.0768.2