Software Engineering Task Resolution on SWE-Bench Verified (with Token Usage)
61.6Success Rate (SR)Terminus 2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Terminus 2Model=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06 | 61.6 | 1.47 | |
| HarnessBridgeModel=Qwen3.5-35B-A3B, Harness Category=Auto-Harness2026.06 | 60.2 | 1.13 | |
| mini-SWE-agentModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06 | 59.8 | 5.92 | |
| Meta-HarnessModel=Qwen3.5-35B-A3B, Harness Category=Auto-Harness2026.06 | 59.2 | 1.92 | |
| Qwen-CoderModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06 | 58.8 | 3.86 | |
| OpenHandsModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06 | 52.6 | 1.96 | |
| Meta-HarnessModel=GLM-4.7-Flash, Harness Category=Auto-Harness2026.06 | 49.6 | 2.43 | |
| Terminus-KIRAModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06 | 46 | 9.77 | |
| HarnessBridgeModel=GLM-4.7-Flash, Harness Category=Auto-Harness2026.06 | 46 | 1.48 | |
| mini-SWE-agentModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.06 | 45.4 | 3.91 | |
| Terminus 2Model=GLM-4.7-Flash, Harness Category=Manual Harness2026.06 | 45.2 | 1.51 | |
| OpenHandsModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.06 | 42 | 3.69 | |
| Qwen-CoderModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.06 | 42 | 4.34 | |
| Terminus-KIRAModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.06 | 37.8 | 6.78 |