# Agentic Terminal Interaction on Terminal-Bench v1 Source: [Agentic Terminal Interaction on Terminal-Bench v1]() Collection index: [llms.txt]() Data updated: 2026-06-17T07:54:26.176Z Evaluation of agent performance on tasks requiring interaction within a terminal environment, using the Terminal-Bench v1 dataset, measured by Success Rate. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Agentic Terminal Interaction | | Dataset (including any stated split) | Terminal-Bench v1 | | Metric | Success Rate | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Success Rate | Result date | Report paper | | --- | --- | --- | --- | | Claude-Opus-4.5 | 47.5 | Not recorded | 6a322a57d33dfb23e783ed6c | | Gemini-3-Pro | 46.3 | Not recorded | 6a322a57d33dfb23e783ed6c | | Kimi-K2-Instruct-0905 | 44.5 | Not recorded | 6a322a57d33dfb23e783ed6c | | Qwen3-Coder-480B-A35B-Instruct | 37.5 | Not recorded | 6a322a57d33dfb23e783ed6c | | GLM-4.7 | 36.3 | Not recorded | 6a322a57d33dfb23e783ed6c | | GPT-5.1 | 35 | Not recorded | 6a322a57d33dfb23e783ed6c | | LoopCoder-v2 | 34.2 | Not recorded | 6a322a57d33dfb23e783ed6c | | LoopCoder-v2 | 30 | Not recorded | 6a322a57d33dfb23e783ed6c | | LoopCoder-v2 | 26.3 | Not recorded | 6a322a57d33dfb23e783ed6c | | LoopCoder-v2 | 26.3 | Not recorded | 6a322a57d33dfb23e783ed6c | | DeepSeek-V3.2 | 23.8 | Not recorded | 6a322a57d33dfb23e783ed6c | | Qwen3-235B-A22B-Instruct-2507 | 15 | Not recorded | 6a322a57d33dfb23e783ed6c | | Qwen2.5-Coder-14B-Instruct | 8.8 | Not recorded | 6a322a57d33dfb23e783ed6c | | Seed-Coder-8B-Instruct | 7.5 | Not recorded | 6a322a57d33dfb23e783ed6c | | Qwen2.5-Coder-7B-Instruct | 6.3 | Not recorded | 6a322a57d33dfb23e783ed6c | | DeepSeek-Coder-V2-Lite-Instruct | 5 | Not recorded | 6a322a57d33dfb23e783ed6c | | Qwen2.5-Coder-32B-Instruct | 5 | Not recorded | 6a322a57d33dfb23e783ed6c | ### Claude-Opus-4.5 Success Rate: 47.5. Result ID: 6a3252affbc373592c2fa8d0. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-3-Pro Success Rate: 46.3. Result ID: 6a3252affbc373592c2fa8d1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Kimi-K2-Instruct-0905 Success Rate: 44.5. Result ID: 6a3252affbc373592c2fa8cb. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-Coder-480B-A35B-Instruct Success Rate: 37.5. Result ID: 6a3252affbc373592c2fa8cc. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GLM-4.7 Success Rate: 36.3. Result ID: 6a3252affbc373592c2fa8ce. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.1 Success Rate: 35. Result ID: 6a3252affbc373592c2fa8cf. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LoopCoder-v2 Success Rate: 34.2. Result ID: 6a3252affbc373592c2fa8d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"R (number of refinement loops)":"2"}. This record does not assert independent reproduction. ### LoopCoder-v2 Success Rate: 30. Result ID: 6a3252affbc373592c2fa8d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"R (number of refinement loops)":"3"}. This record does not assert independent reproduction. ### LoopCoder-v2 Success Rate: 26.3. Result ID: 6a3252affbc373592c2fa8d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"R (number of refinement loops)":"1"}. This record does not assert independent reproduction. ### LoopCoder-v2 Success Rate: 26.3. Result ID: 6a3252affbc373592c2fa8d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"R (number of refinement loops)":"4"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 Success Rate: 23.8. Result ID: 6a3252affbc373592c2fa8cd. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-235B-A22B-Instruct-2507 Success Rate: 15. Result ID: 6a3252affbc373592c2fa8ca. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-Coder-14B-Instruct Success Rate: 8.8. Result ID: 6a3252affbc373592c2fa8c8. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Seed-Coder-8B-Instruct Success Rate: 7.5. Result ID: 6a3252affbc373592c2fa8c7. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-Coder-7B-Instruct Success Rate: 6.3. Result ID: 6a3252affbc373592c2fa8c6. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSeek-Coder-V2-Lite-Instruct Success Rate: 5. Result ID: 6a3252affbc373592c2fa8c5. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-Coder-32B-Instruct Success Rate: 5. Result ID: 6a3252affbc373592c2fa8c9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.