Financial Agent Task on FinanceAgent-Terminal
44Accuracy (%)OpenThinkerAgent-32B
Evaluation results
| Method | Links | |
|---|---|---|
| OpenThinkerAgent-32BTrain Size=100K, Method=SFT, Backbone=Qwen3-32B2026.06 | 44 | |
| Nemotron-Terminal-32BTrain Size=264K, Method=SFT, Backbone=Qwen3-32B2026.06 | 40.7 | |
| OT-Agent-ColdSFT+RL-8BBase Model=OpenThinker-Agent-v1-SFT, Train Size=10K+5K, Training Method=SFT+RL2026.06 | 22.7 | |
| OT-Agent-SFT-8B (100K)Base Model=OpenThinker-Agent-v1-SFT, Train Size=100K, Training Method=SFT2026.06 | 17.3 | |
| SERA-32BTrain Size=25K, Method=SFT, Backbone=Qwen3-32B2026.06 | 17.3 | |
| SWE-Lego-Qwen3-32BTrain Size=18K, Method=SFT, Backbone=Qwen3-32B2026.06 | 15.3 | |
| OT-Agent-SFT-8B (10K)Base Model=OpenThinker-Agent-v1-SFT, Train Size=10K, Training Method=SFT2026.06 | 14.7 | |
| SA-SWE-32BTrain Size=4.5K, Method=RL, Backbone=Qwen3-32B2026.06 | 13.3 | |
| Nemotron-Terminal-8BTrain Size=264K, Training Method=SFT2026.06 | 11.3 | |
| Endless TerminalsBase Model=Qwen3-8B, Train Size=15K+3K, Training Method=SFT+RL2026.06 | 10 | |
| DeepSWE-PreviewTrain Size=4.5K, Method=RL, Backbone=Qwen3-32B2026.06 | 10 | |
| Qwen3-32BTrain Size=N/A, Method=N/A, Backbone=Qwen3-32B2026.06 | 9.3 | |
| SWE-Lego-Qwen3-8BBase Model=Qwen3-8B, Train Size=18K, Training Method=SFT2026.06 | 1.3 | |
| Qwen3-8BBase Model=N/A, Train Size=N/A, Training Method=N/A2026.06 | 1.3 |