# Deontic Reasoning on DeonticBench SARA-Bin

Source: [Deontic Reasoning on DeonticBench SARA-Bin](<https://www.sota2.com/research/sota/deontic-reasoning-on-deonticbench-sara-bin>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-04T13:12:01.658Z

Evaluation of model performance on Deontic Reasoning tasks using the DeonticBench SARA-Bin dataset, measured by Macro F1 score.

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-Bin |
| Metric | Macro F1 |
| 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

- [Macro F1](<https://www.sota2.com/research/sota/deontic-reasoning-on-deonticbench-sara-bin.md?metric=Macro%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Macro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3.5-397B | 90.6 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-397B | 88.9 | Not recorded | 6a2106eac10484bac23f0605 |
| Kimi-K2 | 88.5 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-35B | 83.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-35B | 83.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-397B | 83.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-35B | 82.9 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-122B | 82.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-Coder-480B | 80 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-122B | 80 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-122B | 79.9 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-Coder-480B | 79.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-122B | 79.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-397B | 78.2 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-Coder-480B | 76.6 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-122B | 75.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3.5-35B | 74 | Not recorded | 6a2106eac10484bac23f0605 |
| Kimi-K2 | 73.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-235B | 72.1 | Not recorded | 6a2106eac10484bac23f0605 |
| Kimi-K2 | 68.4 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-235B | 66.5 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-235B | 66.5 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-Coder-480B | 59.8 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-235B | 59.8 | Not recorded | 6a2106eac10484bac23f0605 |
| GPT-5.2 | 59.7 | Not recorded | 6a2106eac10484bac23f0605 |
| Kimi-K2 | 59.3 | Not recorded | 6a2106eac10484bac23f0605 |
| Qwen3-Coder-480B | 59.1 | Not recorded | 6a2106eac10484bac23f0605 |
| GPT-5.2 | 56.9 | Not recorded | 6a2106eac10484bac23f0605 |
| GPT-5.2 | 53.1 | Not recorded | 6a2106eac10484bac23f0605 |
| GPT-5.2 | 46.4 | Not recorded | 6a2106eac10484bac23f0605 |

### Qwen3.5-397B

Macro F1: 90.6. Result ID: 6a21799efbc373592c1ee476.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### Qwen3.5-397B

Macro F1: 88.9. Result ID: 6a21799efbc373592c1ee477.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction.

### Kimi-K2

Macro F1: 88.5. Result ID: 6a21799efbc373592c1ee47f.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### Qwen3.5-35B

Macro F1: 83.3. Result ID: 6a21799efbc373592c1ee471.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### Qwen3.5-35B

Macro F1: 83.3. Result ID: 6a21799efbc373592c1ee473.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction.

### Qwen3.5-397B

Macro F1: 83.3. Result ID: 6a21799efbc373592c1ee475.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### Qwen3.5-35B

Macro F1: 82.9. Result ID: 6a21799efbc373592c1ee472.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### Qwen3.5-122B

Macro F1: 82.3. Result ID: 6a21799efbc373592c1ee46e.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### Qwen3-Coder-480B

Macro F1: 80. Result ID: 6a21799efbc373592c1ee46a.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction.

### Qwen3.5-122B

Macro F1: 80. Result ID: 6a21799efbc373592c1ee46d.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### Qwen3.5-122B

Macro F1: 79.9. Result ID: 6a21799efbc373592c1ee46c.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction.

### Qwen3-Coder-480B

Macro F1: 79.3. Result ID: 6a21799efbc373592c1ee468.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### Qwen3.5-122B

Macro F1: 79.3. Result ID: 6a21799efbc373592c1ee46f.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"claude-code"}. This record does not assert independent reproduction.

### Qwen3.5-397B

Macro F1: 78.2. Result ID: 6a21799efbc373592c1ee474.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### Qwen3-Coder-480B

Macro F1: 76.6. Result ID: 6a21799efbc373592c1ee469.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### Qwen3.5-122B

Macro F1: 75.3. Result ID: 6a21799efbc373592c1ee46b.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### Qwen3.5-35B

Macro F1: 74. Result ID: 6a21799efbc373592c1ee470.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### Kimi-K2

Macro F1: 73.3. Result ID: 6a21799efbc373592c1ee47d.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction.

### Qwen3-235B

Macro F1: 72.1. Result ID: 6a21799efbc373592c1ee479.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction.

### Kimi-K2

Macro F1: 68.4. Result ID: 6a21799efbc373592c1ee47c.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### Qwen3-235B

Macro F1: 66.5. Result ID: 6a21799efbc373592c1ee478.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### Qwen3-235B

Macro F1: 66.5. Result ID: 6a21799efbc373592c1ee47b.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### Qwen3-Coder-480B

Macro F1: 59.8. Result ID: 6a21799efbc373592c1ee467.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction.

### Qwen3-235B

Macro F1: 59.8. Result ID: 6a21799efbc373592c1ee47a.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### GPT-5.2

Macro F1: 59.7. Result ID: 6a21799efbc373592c1ee480.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### Kimi-K2

Macro F1: 59.3. Result ID: 6a21799efbc373592c1ee47e.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4a1e209131cea823a1.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### Qwen3-Coder-480B

Macro F1: 59.1. Result ID: 6a21799efbc373592c1ee466.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Harness":"direct"}. This record does not assert independent reproduction.

### GPT-5.2

Macro F1: 56.9. Result ID: 6a21799efbc373592c1ee483.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Harness":"terminus-kira"}. This record does not assert independent reproduction.

### GPT-5.2

Macro F1: 53.1. Result ID: 6a21799efbc373592c1ee482.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Harness":"terminus-2"}. This record does not assert independent reproduction.

### GPT-5.2

Macro F1: 46.4. Result ID: 6a21799efbc373592c1ee481.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106eac10484bac23f0605.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Harness":"codex"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
