# Terminal Agent Tasks on OpenThoughts TBLite Source: [Terminal Agent Tasks on OpenThoughts TBLite]() Collection index: [llms.txt]() Data updated: 2026-05-26T08:41:09.187Z Evaluation of model performance on terminal agent tasks using the OpenThoughts TBLite dataset, 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) | OpenThoughts TBLite | | 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 | | --- | --- | --- | --- | | Qwen3-14B | 15.1 | Not recorded | 6a152931dbd7150506f7dfe2 | | OT-SFT | 12.9 | Not recorded | 6a152931dbd7150506f7dfe2 | | OT-SFT | 11.6 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-8B | 11.4 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-14B | 9.8 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-8B | 9.5 | Not recorded | 6a152931dbd7150506f7dfe2 | | OT-SFT | 6 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-14B | 5.7 | Not recorded | 6a152931dbd7150506f7dfe2 | | Qwen3-8B | 4.9 | Not recorded | 6a152931dbd7150506f7dfe2 | ### Qwen3-14B Pass@1: 15.1. Result ID: 6a155c9ffbc373592c0cd129. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"ECHO"}. This record does not assert independent reproduction. ### OT-SFT Pass@1: 12.9. Result ID: 6a155c9ffbc373592c0cd126. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"ECHO"}. This record does not assert independent reproduction. ### OT-SFT Pass@1: 11.6. Result ID: 6a155c9ffbc373592c0cd125. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"GRPO"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1: 11.4. Result ID: 6a155c9ffbc373592c0cd123. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"ECHO"}. This record does not assert independent reproduction. ### Qwen3-14B Pass@1: 9.8. Result ID: 6a155c9ffbc373592c0cd128. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"GRPO"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1: 9.5. Result ID: 6a155c9ffbc373592c0cd122. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"GRPO"}. This record does not assert independent reproduction. ### OT-SFT Pass@1: 6. Result ID: 6a155c9ffbc373592c0cd124. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"SFT"}. This record does not assert independent reproduction. ### Qwen3-14B Pass@1: 5.7. Result ID: 6a155c9ffbc373592c0cd127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Setup":"Base"}. This record does not assert independent reproduction. ### Qwen3-8B Pass@1: 4.9. Result ID: 6a155c9ffbc373592c0cd121. [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.