List your company

Multimodal Search on IMEB

55.3AccuracyKimi-K2.5
1.2215.2629.343.34May 8, 2026

Evaluation results

MethodLinks
Kimi-K2.5Evaluation Mode=Agentic Workflow2026.0555.38.8
HyperEyes-235BTraining Stage=RL, Evaluation Mode=Agentic Workflow2026.0552.73
Gemini-3.1-ProEvaluation Mode=Agentic Workflow2026.0551.32.1
HyperEyes-235BTraining Stage=SFT, Evaluation Mode=Agentic Workflow2026.05503.3
HyperEyes-30BTraining Stage=RL, Evaluation Mode=Agentic Workflow2026.0546.73.1
HyperEyes-30BTraining Stage=SFT, Evaluation Mode=Agentic Workflow2026.05423.8
Claude-Opus-4.6Evaluation Mode=Agentic Workflow2026.0541.73.4
Gemini-3.1-ProEvaluation Mode=Direct Answer2026.0540.8—
Qwen3-VL-235BEvaluation Mode=Agentic Workflow2026.05304.8
Kimi-K2.5Evaluation Mode=Direct Answer2026.0527.7—
Claude-Opus-4.6Evaluation Mode=Direct Answer2026.0527—
VDREvaluation Mode=Multimodal Deep Search Agents2026.0521.212.3
DeepEyes-V2Evaluation Mode=Multimodal Deep Search Agents2026.05184.7
Qwen3-VL-30BEvaluation Mode=Agentic Workflow2026.0517.74.3
WebWatcherEvaluation Mode=Multimodal Deep Search Agents2026.0515.37.8
Qwen3-VL-235BEvaluation Mode=Direct Answer2026.0512—
Qwen3-VL-30BEvaluation Mode=Direct Answer2026.056.7—
MMSearch-R1Evaluation Mode=Multimodal Deep Search Agents2026.053.31.9