# Terminal Agent Tasks on val100 (val) Source: [Terminal Agent Tasks on val100 (val)]() Collection index: [llms.txt]() Data updated: 2026-05-26T08:41:09.130Z Evaluation of agent performance on terminal agent tasks using the val100 dataset (validation split), measured by pass@1. 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 | Terminal Agent Tasks | | Dataset (including any stated split) | val100 (val) | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | 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 - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | OT-SFT | 73.1 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-14B | 65 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-8B | 63.7 | Not recorded | 6a152931dbd7150506f7dfe2 | | OT-SFT | 63.5 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-14B | 60.3 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-8B | 54.9 | Not recorded | 6a152931dbd7150506f7dfe2 | | OT-SFT | 38.5 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-14B | 35.3 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-8B | 34.2 | Not recorded | 6a152931dbd7150506f7dfe2 | ### OT-SFT Pass@1: 73.1. Result ID: 6a155c9ffbc373592c0cd114. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"ECHO"}. This record does not assert independent reproduction. ### Qwen3-14B Pass@1: 65. Result ID: 6a155c9ffbc373592c0cd117. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"ECHO"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1: 63.7. Result ID: 6a155c9ffbc373592c0cd111. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"ECHO"}. This record does not assert independent reproduction. ### OT-SFT Pass@1: 63.5. Result ID: 6a155c9ffbc373592c0cd113. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"GRPO"}. This record does not assert independent reproduction. ### Qwen3-14B Pass@1: 60.3. Result ID: 6a155c9ffbc373592c0cd116. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"GRPO"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1: 54.9. Result ID: 6a155c9ffbc373592c0cd110. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"GRPO"}. This record does not assert independent reproduction. ### OT-SFT Pass@1: 38.5. Result ID: 6a155c9ffbc373592c0cd112. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"SFT"}. This record does not assert independent reproduction. ### Qwen3-14B Pass@1: 35.3. Result ID: 6a155c9ffbc373592c0cd115. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Base"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1: 34.2. Result ID: 6a155c9ffbc373592c0cd10f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Base"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.