List your company

Morphology Reasoning on Time-MMD Climate (test)

99.18AccuracyDeepSeek-R1
40.607255.813671.0286.2264May 28, 2026

Evaluation results

MethodLinks
DeepSeek-R1Horizon=96, Category=Advanced Models (reference only)2026.0599.18
KAIROSAGENT-4B (+ Turn-Level Reward RL)Horizon=96, Category=Comparable-Scale Models2026.0598.08
GPT-5.2Horizon=96, Category=Advanced Models (reference only)2026.0597.8
KAIROSAGENT-4B (SFT-Only)Horizon=96, Category=Comparable-Scale Models2026.0597.8
KAIROSAGENT-4B (+ Outcome-Level Reward RL)Horizon=96, Category=Comparable-Scale Models2026.0596.7
Llama-3.1-8B-InstructHorizon=96, Category=Comparable-Scale Models2026.0552.47
DeepSeek-R1-Distill-Qwen-7BHorizon=96, Category=Comparable-Scale Models2026.0542.86