Coding on Aider Polyglot
18.8AccuracyEndless Terminals
Evaluation results
| Method | Links | |
|---|---|---|
| Endless TerminalsBase Model=Qwen3-8B, Train Size=15K+3K, Training Method=SFT+RL2026.06 | 18.8 | |
| OT-Agent-ColdSFT+RL-8BBase Model=OpenThinker-Agent-v1-SFT, Train Size=10K+5K, Training Method=SFT+RL2026.06 | 18.1 | |
| OT-Agent-SFT-8B (100K)Base Model=OpenThinker-Agent-v1-SFT, Train Size=100K, Training Method=SFT2026.06 | 15.9 | |
| OT-Agent-SFT-8B (10K)Base Model=OpenThinker-Agent-v1-SFT, Train Size=10K, Training Method=SFT2026.06 | 14.2 | |
| Nemotron-Terminal-8BTrain Size=264K, Training Method=SFT2026.06 | 12.6 | |
| Qwen3-8BBase Model=N/A, Train Size=N/A, Training Method=N/A2026.06 | 11.7 | |
| SWE-Lego-Qwen3-8BBase Model=Qwen3-8B, Train Size=18K, Training Method=SFT2026.06 | 3.7 |