Question Answering on General questions
61.2Correct RateZEPHYRUS-REFLECTIVE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ZEPHYRUS-REFLECTIVELLM=gpt-5-mini2025.10 | 61.2 | 99.2 | 0.25 | 60.6 | |
| ZEPHYRUS-REFLECTIVELLM=gpt-5.22025.10 | 58.9 | 98.9 | 0.27 | 58 | |
| ZEPHYRUS-DIRECTLLM=gpt-5-mini2025.10 | 58.5 | 99.2 | 0.09 | 61.5 | |
| ZEPHYRUS-DIRECTLLM=gpt-5.22025.10 | 57.7 | 99.5 | 0.16 | 58.5 | |
| ZEPHYRUS-REFLECTIVELLM=gpt-oss-120b2025.10 | 56.2 | 99.1 | 0.11 | 59.3 | |
| ZEPHYRUS-DIRECTLLM=gemini-2.5-flash2025.10 | 56 | 99.1 | 0.07 | 61.6 | |
| ZEPHYRUS-DIRECTLLM=gpt-oss-120b2025.10 | 55.4 | 98.3 | 0.08 | 57.1 | |
| ZEPHYRUS-REFLECTIVELLM=gemini-2.5-flash2025.10 | 52.5 | 97.2 | 0.1 | 61.8 | |
| ZEPHYRUS-DIRECTLLM=qwen3-30b2025.10 | 51.2 | 96.3 | 0.06 | 59.8 | |
| ZEPHYRUS-REFLECTIVELLM=qwen3-30b2025.10 | 44.2 | 83.6 | 0.06 | 48.6 | |
| Text Only LLMLLM=gpt-5.22025.10 | 17.6 | 97.5 | 0.1 | 42.5 | |
| Text Only LLMLLM=gpt-5-mini2025.10 | 17 | 98.6 | 0.07 | 53 | |
| Text Only LLMLLM=qwen3-30b2025.10 | 16.4 | 93 | 0.03 | 8.97 | |
| Text Only LLMLLM=gemini-2.5-flash2025.10 | 15.7 | 90.8 | 0.06 | 24.3 | |
| Text Only LLMLLM=gpt-oss-120b2025.10 | 13.3 | 68.8 | 0.02 | 25 |