List your company

Deontic Reasoning on DeonticBench SARA-Num

77.1AccuracyQwen3.5-397B
5.65224.20142.7561.299Jun 3, 2026

Evaluation results

MethodLinks
Qwen3.5-397BHarness=terminus-kira2026.0677.1
GPT-5.2Harness=terminus-kira2026.0660
Qwen3.5-397BHarness=direct2026.0652.8
Qwen3.5-397BHarness=claude-code2026.0651.4
GPT-5.2Harness=terminus-22026.0651.4
Qwen3.5-35BHarness=claude-code2026.0637.1
Qwen3.5-122BHarness=direct2026.0637
Qwen3-Coder-480BHarness=claude-code2026.0634.3
GPT-5.2Harness=codex2026.0634.3
Qwen3.5-35BHarness=direct2026.0634
Qwen3-235BHarness=direct2026.0632.1
GPT-5.2Harness=direct2026.0630.3
Qwen3.5-122BHarness=claude-code2026.0628.6
Qwen3.5-397BHarness=terminus-22026.0628.6
Qwen3-235BHarness=terminus-kira2026.0628.6
Qwen3-Coder-480BHarness=direct2026.0624.9
Qwen3.5-122BHarness=codex2026.0622.9
Qwen3.5-35BHarness=terminus-22026.0622.9
Kimi-K2Harness=terminus-kira2026.0622.9
Qwen3.5-122BHarness=terminus-22026.0620
Qwen3.5-122BHarness=terminus-kira2026.0620
Kimi-K2Harness=codex2026.0620
Qwen3-235BHarness=terminus-22026.0617.1
Qwen3-Coder-480BHarness=terminus-22026.0614.3
Qwen3-Coder-480BHarness=terminus-kira2026.0614.3
Qwen3.5-35BHarness=terminus-kira2026.0611.4
Qwen3-235BHarness=codex2026.0611.4
Kimi-K2Harness=terminus-22026.0611.4
Qwen3-Coder-480BHarness=codex2026.068.6
Kimi-K2Harness=direct2026.068.4