Question Answering on TriviaQA (TriviaQA, Average)
77.3TriviaQA ScoreLLM-PeerReview
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLM-PeerReview2025.12 | 77.3 | 61.9 | |
| LLM-PeerReview-W2025.12 | 77.3 | 62.3 | |
| Smoothie-LocalScope=Local2025.12 | 74 | 53.8 | |
| Qwen2.5-14B-InstructScale=13B-14B2025.12 | 73.5 | 54 | |
| Smoothie-GlobalScope=Global2025.12 | 73.5 | 54 | |
| Agent-Forest2025.12 | 73 | 56.8 | |
| Qwen2.5-14B-Instruct-1MScale=13B-14B2025.12 | 69.5 | 53 | |
| Phi-3-medium-4k-instructScale=13B-14B2025.12 | 68 | 41 | |
| Random2025.12 | 67.7 | 46.9 | |
| Theoretical average2025.12 | 67.6 | 46.6 | |
| DeepSeek-R1-Distill-Qwen-14BScale=13B-14B2025.12 | 59.5 | 38.5 |