Time Prediction on time tasks
0Absolute Error (Q25)ZEPHYRUS-REFLECTIVE
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| ZEPHYRUS-REFLECTIVELLM=gpt-5.22025.10 | 0 | 0 | 12 | 99.7 | |
| ZEPHYRUS-DIRECTLLM=gpt-5.22025.10 | 0 | 0 | 12 | 99.7 | |
| ZEPHYRUS-REFLECTIVELLM=gpt-5-mini2025.10 | 0 | 0 | 3 | 73.4 | |
| ZEPHYRUS-DIRECTLLM=gpt-5-mini2025.10 | 0 | 0 | 6 | 66 | |
| ZEPHYRUS-REFLECTIVELLM=gemini-2.5-flash2025.10 | 0 | 0 | 0 | 105.8 | |
| ZEPHYRUS-DIRECTLLM=gemini-2.5-flash2025.10 | 0 | 0 | 0 | 160.1 | |
| ZEPHYRUS-REFLECTIVELLM=gpt-oss-120b2025.10 | 0 | 0 | 0 | 45.7 | |
| ZEPHYRUS-DIRECTLLM=gpt-oss-120b2025.10 | 0 | 0 | 0 | 39.8 | |
| ZEPHYRUS-REFLECTIVELLM=qwen3-30b2025.10 | 0 | 0 | 6 | 87.6 | |
| ZEPHYRUS-DIRECTLLM=qwen3-30b2025.10 | 0 | 0 | 0 | 60 | |
| Text Only LLMLLM=gpt-5.22025.10 | 6 | 18 | 36 | 135.7 | |
| Text Only LLMLLM=gpt-5-mini2025.10 | 6 | 12 | 36 | 103.4 | |
| Text Only LLMLLM=gemini-2.5-flash2025.10 | 6 | 18 | 42 | 129.1 | |
| Text Only LLMLLM=gpt-oss-120b2025.10 | 6 | 18 | 36 | 114 | |
| Text Only LLMLLM=qwen3-30b2025.10 | 6 | 24 | 54 | 151.4 |