Terminal-related CLI agent task on TerminalBench 2.0
57.8AccuracyClaude-Opus-4.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude-Opus-4.5Model Size=-, Agent Scaffolds=Terminus-22026.04 | 57.8 | — | |
| Gemini-3-Pro-PreviewModel Size=-, Agent Scaffolds=Terminus-22026.04 | 56.9 | — | |
| GPT-5.2Model Size=-, Agent Scaffolds=Terminus-22026.04 | 54 | — | |
| Gemini-3-Flash-PreviewModel Size=-, Agent Scaffolds=Terminus-22026.04 | 51.7 | — | |
| GPT-5.1Model Size=-, Agent Scaffolds=Terminus-22026.04 | 47.6 | — | |
| TACOBackbone=MiniMax-2.52026.04 | 44.16 | 110.63 | |
| Minimax-M2.5Model Size=230B, Agent Scaffolds=TACO+Terminus-22026.04 | 44.16 | — | |
| BaselineBackbone=MiniMax-2.52026.04 | 42.8 | 113.74 | |
| Claude-Sonnet-4.5Model Size=-, Agent Scaffolds=Terminus-22026.04 | 42.8 | — | |
| Minimax-M2.5Model Size=230B, Agent Scaffolds=Terminus-22026.04 | 42.8 | — | |
| DeepSeek-V3.2Model Size=685B, Agent Scaffolds=TACO+Terminus-22026.04 | 42.77 | — | |
| GLM-4.7Model Size=358B, Agent Scaffolds=Terminus-22026.04 | 41 | — | |
| DeepSeek-V3.2Model Size=685B, Agent Scaffolds=Terminus-22026.04 | 40.62 | — | |
| DeepSeek-V3.1-Nex-N1Model Size=685B, Agent Scaffolds=OpenHands2026.04 | 31.8 | — | |
| Minimax-M2.1Model Size=229B, Agent Scaffolds=Terminus-22026.04 | 29.2 | — | |
| Kimi-K2-InstructModel Size=1T, Agent Scaffolds=Terminus-22026.04 | 27.8 | — | |
| Qwen3-Coder-480B-InstructModel Size=480B, Agent Scaffolds=TACO+Terminus-22026.04 | 25.86 | — | |
| Qwen3-Coder-480BModel Size=480B, Agent Scaffolds=Terminus-22026.04 | 23.9 | — | |
| Qwen3-32B-Nex-N1Model Size=32B, Agent Scaffolds=OpenHands2026.04 | 16.7 | — | |
| Qwen3-Coder-30B-A3B-InstructModel Size=30B, Agent Scaffolds=Terminus-22026.04 | 14.6 | — | |
| Qwen3-235B-A22B-InstructModel Size=235B, Agent Scaffolds=Terminus-22026.04 | 13.5 | — | |
| Qwen3-30B-A3B-Nex-N1Model Size=30B, Agent Scaffolds=OpenHands2026.04 | 8.3 | — | |
| Qwen3-32B-InstructModel Size=32B, Agent Scaffolds=TACO+Terminus-22026.04 | 7.48 | — | |
| Qwen3-14B-InstructModel Size=14B, Agent Scaffolds=TACO+Terminus-22026.04 | 6.15 | — | |
| Qwen3-14B-InstructModel Size=14B, Agent Scaffolds=Terminus-22026.04 | 4.04 | — | |
| Qwen3-32B-InstructModel Size=32B, Agent Scaffolds=Terminus-22026.04 | 3.92 | — | |
| Qwen3-8B-InstructModel Size=8B, Agent Scaffolds=TACO+Terminus-22026.04 | 3.67 | — | |
| Qwen3-32B-InstructModel Size=32B, Agent Scaffolds=OpenHands2026.04 | 3.4 | — | |
| Qwen3-8B-InstructModel Size=8B, Agent Scaffolds=Terminus-22026.04 | 1.43 | — |