List your company

Morphology Reasoning on Time-MMD Energy (test)

84.12AccuracyGPT-5.2
1.918423.259244.665.9408May 28, 2026

Evaluation results

MethodLinks
GPT-5.2Horizon=96, Category=Advanced Models (reference only)2026.0584.12
DeepSeek-R1Horizon=96, Category=Advanced Models (reference only)2026.0579.51
KAIROSAGENT-4B (+ Turn-Level Reward RL)Horizon=96, Category=Comparable-Scale Models2026.0550.47
KAIROSAGENT-4B (SFT-Only)Horizon=96, Category=Comparable-Scale Models2026.0545.21
KAIROSAGENT-4B (+ Outcome-Level Reward RL)Horizon=96, Category=Comparable-Scale Models2026.0543.33
Llama-3.1-8B-InstructHorizon=96, Category=Comparable-Scale Models2026.0538.72
DeepSeek-R1-Distill-Qwen-7BHorizon=96, Category=Comparable-Scale Models2026.055.08