Text Generation on TemporalBench
34.2TemporalBench ScoreOrca
Evaluation Results
| Method | Links | |
|---|---|---|
| OrcaSize (B)=42026.06 | 34.2 | |
| V-JEPA 2.1 (+LLaMA3-8B)Size (B)=102026.06 | 28.5 | |
| Qwen3.5Size (B)=42026.06 | 25.2 | |
| OrcaSize (B)=0.82026.06 | 22.6 | |
| MiniCPM-V-4.6Size (B)=22026.06 | 21.2 | |
| DeepSeek-VL2Size (B)=32026.06 | 21 | |
| Gemma 4Size (B)=42026.06 | 20.2 | |
| Qwen3.5Size (B)=0.82026.06 | 19.1 | |
| SmolVLM2Size (B)=22026.06 | 18.4 | |
| Gemma 4Size (B)=22026.06 | 17.1 | |
| Emu3Size (B)=82026.06 | 9.5 | |
| Emu3.5Size (B)=342026.06 | 9.5 |