Multi-choice ranking on Multi-Condition Ranking (test)
99.2AccuracyEP+SEM_CRIT
Evaluation Results
| Method | Links | |
|---|---|---|
| EP+SEM_CRITModel=gpt-5-2025-08-072025.10 | 99.2 | |
| EP+SEM_CRITModel=gpt-5-2025-08-072025.10 | 99.2 | |
| SEM_CRITModel=gpt-5-2025-08-072025.10 | 98 | |
| SEM_CRITModel=gpt-5-2025-08-072025.10 | 98 | |
| EP_CRITModel=gpt-5-2025-08-072025.10 | 96.8 | |
| EP_CRITModel=gpt-5-2025-08-072025.10 | 96.8 | |
| EP_LABELModel=gpt-5-2025-08-072025.10 | 95.2 | |
| EP_LABELModel=gpt-5-2025-08-072025.10 | 95.2 | |
| zero_shotModel=gpt-5-2025-08-072025.10 | 81.6 | |
| zero_shotModel=gpt-5-2025-08-072025.10 | 81.6 | |
| EP+SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 72.8 | |
| EP+SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 72.8 | |
| SEM_CRITModel=gpt-oss-20b2025.10 | 72 | |
| SEM_CRITModel=gpt-oss-20b2025.10 | 72 | |
| SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 65.6 | |
| SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 65.6 | |
| EP_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 64.5 | |
| EP_CRITModel=qwen3-vl-235b-a22b-thinking2025.10 | 64.5 | |
| EP+SEM_CRITModel=gpt-oss-20b2025.10 | 58.8 | |
| EP+SEM_CRITModel=gpt-oss-20b2025.10 | 58.8 | |
| zero_shotModel=gpt-oss-20b2025.10 | 58 | |
| zero_shotModel=gpt-oss-20b2025.10 | 58 | |
| EP_CRITModel=gpt-oss-20b2025.10 | 57.6 | |
| EP_CRITModel=gpt-oss-20b2025.10 | 57.6 | |
| EP_CRITModel=qwen3-235b-a22b-instruct-25072025.10 | 56.8 | |
| EP+SEM_CRITModel=qwen3-235b-a22b-instruct-25072025.10 | 54 | |
| EP_LABELModel=qwen3-vl-235b-a22b-thinking2025.10 | 50.4 | |
| EP_LABELModel=qwen3-vl-235b-a22b-thinking2025.10 | 50.4 | |
| zero_shotModel=qwen3-vl-235b-a22b-thinking2025.10 | 46.2 | |
| zero_shotModel=qwen3-vl-235b-a22b-thinking2025.10 | 46.2 | |
| EP_LABELModel=qwen3-235b-a22b-instruct-25072025.10 | 44 | |
| SEM_CRITModel=qwen3-235b-a22b-instruct-25072025.10 | 42.4 | |
| zero_shotModel=qwen3-235b-a22b-instruct-25072025.10 | 42 | |
| zero_shotModel=llama-4-scout2025.10 | 38.8 | |
| SEM_CRITModel=llama-4-scout2025.10 | 38.8 | |
| EP_LABELModel=llama-4-scout2025.10 | 37.2 | |
| EP+SEM_CRITModel=gpt-4o-mini-2024-07-182025.10 | 36.8 | |
| EP_CRITModel=llama-4-scout2025.10 | 36.8 | |
| zero_shotModel=gpt-4o-mini-2024-07-182025.10 | 35.2 | |
| EP_CRITModel=gpt-4o-mini-2024-07-182025.10 | 34.8 | |
| EP+SEM_CRITModel=llama-4-scout2025.10 | 34.8 | |
| EP_LABELModel=gpt-oss-20b2025.10 | 34 | |
| EP_LABELModel=gpt-oss-20b2025.10 | 34 | |
| SEM_CRITModel=gpt-4o-mini-2024-07-182025.10 | 32.8 | |
| EP_LABELModel=gpt-4o-mini-2024-07-182025.10 | 32 |