List your company

Logical Reasoning on Maze

98Pass@1Kimi K2.5 + ETCHR
-3.9222.544975.46May 22, 2026

Evaluation results

MethodLinks
Kimi K2.5 + ETCHRTemperature=02026.0598
Kimi K2.5Temperature=02026.0595.5
Gemini-3.1-Flash-Lite + ETCHRTemperature=02026.0551.5
Gemini-3.1-Flash-LiteTemperature=02026.0540
Qwen3-VL-8B + ETCHRTemperature=02026.0538.5
Qwen3-VL-8BTemperature=02026.0527.5
ThinkMorph-7BTemperature=0, Max image generations=102026.056.5
DeepEyesV2Temperature=0, Max tool invocations=102026.050.5
ThymeTemperature=0, Max tool invocations=102026.050
Bagel-Zebra-CoTTemperature=0, Max image generations=102026.050