# Deontic Reasoning on DeonticBench SARA-Num Source: [Deontic Reasoning on DeonticBench SARA-Num]() Collection index: [llms.txt]() Data updated: 2026-06-04T13:12:01.592Z Evaluation of model performance on Deontic Reasoning tasks using the DeonticBench SARA-Num dataset, measured by Accuracy. 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 | Deontic Reasoning | | Dataset (including any stated split) | DeonticBench SARA-Num | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 30 of 30 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen3.5-397B | 77.1 | Not recorded | 6a2106eac10484bac23f0605 | | GPT-5.2 | 60 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-397B | 52.8 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-397B | 51.4 | Not recorded | 6a2106eac10484bac23f0605 | | GPT-5.2 | 51.4 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-35B | 37.1 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-122B | 37 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-Coder-480B | 34.3 | Not recorded | 6a2106eac10484bac23f0605 | | GPT-5.2 | 34.3 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-35B | 34 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-235B | 32.1 | Not recorded | 6a2106eac10484bac23f0605 | | GPT-5.2 | 30.3 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-122B | 28.6 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-397B | 28.6 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-235B | 28.6 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-Coder-480B | 24.9 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-122B | 22.9 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-35B | 22.9 | Not recorded | 6a2106eac10484bac23f0605 | | Kimi-K2 | 22.9 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-122B | 20 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-122B | 20 | Not recorded | 6a2106eac10484bac23f0605 | | Kimi-K2 | 20 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-235B | 17.1 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-Coder-480B | 14.3 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-Coder-480B | 14.3 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3.5-35B | 11.4 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-235B | 11.4 | Not recorded | 6a2106eac10484bac23f0605 | | Kimi-K2 | 11.4 | Not recorded | 6a2106eac10484bac23f0605 | | Qwen3-Coder-480B | 8.6 | Not recorded | 6a2106eac10484bac23f0605 | | Kimi-K2 | 8.4 | Not recorded | 6a2106eac10484bac23f0605 | ### Qwen3.5-397B Accuracy: 77.1. Result ID: 6a21799efbc373592c1ee43a. [Reporting paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### GPT-5.2 Accuracy: 60. Result ID: 6a21799efbc373592c1ee447. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### Qwen3.5-397B Accuracy: 52.8. Result ID: 6a21799efbc373592c1ee438. [Reporting paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. ### Qwen3.5-397B Accuracy: 51.4. Result ID: 6a21799efbc373592c1ee43b. [Reporting paper]() Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction. ### GPT-5.2 Accuracy: 51.4. Result ID: 6a21799efbc373592c1ee446. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Qwen3.5-35B Accuracy: 37.1. Result ID: 6a21799efbc373592c1ee437. [Reporting paper]() Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction. ### Qwen3.5-122B Accuracy: 37. Result ID: 6a21799efbc373592c1ee42f. [Reporting paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. ### Qwen3-Coder-480B Accuracy: 34.3. Result ID: 6a21799efbc373592c1ee42e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction. ### GPT-5.2 Accuracy: 34.3. Result ID: 6a21799efbc373592c1ee445. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction. ### Qwen3.5-35B Accuracy: 34. Result ID: 6a21799efbc373592c1ee434. [Reporting paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. ### Qwen3-235B Accuracy: 32.1. Result ID: 6a21799efbc373592c1ee43c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. ### GPT-5.2 Accuracy: 30.3. Result ID: 6a21799efbc373592c1ee444. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. ### Qwen3.5-122B Accuracy: 28.6. Result ID: 6a21799efbc373592c1ee433. [Reporting paper]() Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction. ### Qwen3.5-397B Accuracy: 28.6. Result ID: 6a21799efbc373592c1ee439. [Reporting paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Qwen3-235B Accuracy: 28.6. Result ID: 6a21799efbc373592c1ee43f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### Qwen3-Coder-480B Accuracy: 24.9. Result ID: 6a21799efbc373592c1ee42a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. ### Qwen3.5-122B Accuracy: 22.9. Result ID: 6a21799efbc373592c1ee430. [Reporting paper]() Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction. ### Qwen3.5-35B Accuracy: 22.9. Result ID: 6a21799efbc373592c1ee435. [Reporting paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Kimi-K2 Accuracy: 22.9. Result ID: 6a21799efbc373592c1ee443. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### Qwen3.5-122B Accuracy: 20. Result ID: 6a21799efbc373592c1ee431. [Reporting paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Qwen3.5-122B Accuracy: 20. Result ID: 6a21799efbc373592c1ee432. [Reporting paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### Kimi-K2 Accuracy: 20. Result ID: 6a21799efbc373592c1ee441. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction. ### Qwen3-235B Accuracy: 17.1. Result ID: 6a21799efbc373592c1ee43e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Qwen3-Coder-480B Accuracy: 14.3. Result ID: 6a21799efbc373592c1ee42c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Qwen3-Coder-480B Accuracy: 14.3. Result ID: 6a21799efbc373592c1ee42d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### Qwen3.5-35B Accuracy: 11.4. Result ID: 6a21799efbc373592c1ee436. [Reporting paper]() Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction. ### Qwen3-235B Accuracy: 11.4. Result ID: 6a21799efbc373592c1ee43d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction. ### Kimi-K2 Accuracy: 11.4. Result ID: 6a21799efbc373592c1ee442. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction. ### Qwen3-Coder-480B Accuracy: 8.6. Result ID: 6a21799efbc373592c1ee42b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction. ### Kimi-K2 Accuracy: 8.4. Result ID: 6a21799efbc373592c1ee440. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.