Morphology Reasoning on Time-MMD Climate (test)
99.18AccuracyDeepSeek-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1Horizon=96, Category=Advanced Models (reference only)2026.05 | 99.18 | |
| KAIROSAGENT-4B (+ Turn-Level Reward RL)Horizon=96, Category=Comparable-Scale Models2026.05 | 98.08 | |
| GPT-5.2Horizon=96, Category=Advanced Models (reference only)2026.05 | 97.8 | |
| KAIROSAGENT-4B (SFT-Only)Horizon=96, Category=Comparable-Scale Models2026.05 | 97.8 | |
| KAIROSAGENT-4B (+ Outcome-Level Reward RL)Horizon=96, Category=Comparable-Scale Models2026.05 | 96.7 | |
| Llama-3.1-8B-InstructHorizon=96, Category=Comparable-Scale Models2026.05 | 52.47 | |
| DeepSeek-R1-Distill-Qwen-7BHorizon=96, Category=Comparable-Scale Models2026.05 | 42.86 |