Temporal and Causal Reasoning on NEXT-QA (test)
30.3WUPSLlama 3-V 70B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama 3-V 70BZero-shot=true, Parameters=70B2024.07 | 30.3 | |
| Gemini 1.0 UltraZero-shot=true2024.07 | 29.9 | |
| Gemini 1.0 ProZero-shot=true2024.07 | 28 | |
| Llama 3-V 8BZero-shot=true, Parameters=8B2024.07 | 27.3 |