General Reasoning Average on PostTrainBench
44.81Average (%)Official Instruct Model
Evaluation Results
| Method | Links | |
|---|---|---|
| Official Instruct ModelProtocol=Official Instruct, Backbone=SmolLM3-3B2026.05 | 44.81 | |
| GLM-4.7 & ANDES (Ours)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.05 | 31.91 | |
| Opus-4.6 (1M)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 28.52 | |
| Opus-4.7 (xHigh)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 25.28 | |
| Opus-4.6Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 23.16 | |
| Gemini-3.1-ProProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 22.08 | |
| GPT-5.2Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 21.26 | |
| GPT-5.4 (High)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 20.72 | |
| GLM-4.7 (Scaffold-only)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.05 | 20.12 | |
| MiniMax-M2.5Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 9.04 | |
| GPT-5.1-Codex-MaxProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 8.21 | |
| MiniMax-M2.1Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 5.3 | |
| Base Model (SmolLM3-3B)Protocol=Zero-Shot, Backbone=SmolLM3-3B2026.05 | 4.52 | |
| Kimi-K2-ThinkingProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 4.52 | |
| Qwen3-MaxProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 4.5 | |
| Sonnet-4.5Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.05 | 3.99 | |
| GLM-4.7 (OpenCode)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.05 | 3.53 |