List your company

Terminal-based agent interaction on Terminal-Bench 2.0

59.3Success Rate (SR)Claude-Opus-4.5
-2.37213.63929.6545.661Jun 11, 2026Jun 12, 2026Jun 13, 2026Jun 14, 2026Jun 15, 2026Jun 16, 2026

Evaluation results

MethodLinks
Claude-Opus-4.52026.0659.3—
Gemini-3-Pro2026.0654.2—
GPT-5.12026.0647.6—
DeepSeek-V3.22026.0646.4—
GLM-4.72026.0641—
HarnessBridgeModel=Qwen3.5-35B-A3B, Harness Category=Auto-Harness2026.0633.71.23
Meta-HarnessModel=Qwen3.5-35B-A3B, Harness Category=Auto-Harness2026.0631.52.2
Terminus 2Model=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.0630.32.31
mini-SWE-agentModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.0629.26.32
Kimi-K2-Instruct-09052026.0627.8—
Terminus-KIRAModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06279.59
OpenHandsModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.06272.61
Qwen-CoderModel=Qwen3.5-35B-A3B, Harness Category=Manual Harness2026.0624.74.19
Qwen3-Coder-480B-A35B-Instruct2026.0623.6—
LoopCoder-v2R (number of refinement loops)=22026.0621—
HarnessBridgeModel=GLM-4.7-Flash, Harness Category=Auto-Harness2026.0620.20.42
Terminus 2Model=GLM-4.7-Flash, Harness Category=Manual Harness2026.0619.11.87
Meta-HarnessModel=GLM-4.7-Flash, Harness Category=Auto-Harness2026.0614.61.33
OpenHandsModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.0613.51.28
Qwen3-235B-A22B-Instruct-25072026.0613.5—
LoopCoder-v2R (number of refinement loops)=12.22026.0612.2—
mini-SWE-agentModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.0611.21.6
LoopCoder-v2R (number of refinement loops)=12026.0611.2—
Qwen-CoderModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.0610.11.41
LoopCoder-v2R (number of refinement loops)=42026.069—
Terminus-KIRAModel=GLM-4.7-Flash, Harness Category=Manual Harness2026.066.74.9
Qwen2.5-Coder-32B-Instruct2026.064.5—
Seed-Coder-8B-Instruct2026.062.5—
Kimi-Dev-72B2026.062.3—
DeepSeek-Coder-V2-Lite-Instruct2026.060—
Qwen2.5-Coder-7B-Instruct2026.060—
Qwen2.5-Coder-14B-Instruct2026.060—