Research Idea Evaluation on ScholarIdeas (Evaluation)
23.33Reference Inv.GPT-5.1 Instant
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.1 Instant2025.10 | 23.33 | |
| Llama-3.3-70B2025.10 | 19.07 | |
| GPT-4.12025.10 | 15.22 | |
| Claude-4-Sonnet2025.10 | 13.9 | |
| GPT-4o-search-previewsearch-enabled=true2025.10 | 1.66 | |
| OpenAI Deep Research2025.10 | 1.07 | |
| DR Tulu2025.10 | 0 | |
| ScholarEval LlamaBackbone=Llama-3.3-70B2025.10 | 0 | |
| ScholarEval GPT-4.1Backbone=GPT-4.12025.10 | 0 | |
| ScholarEval GPT-5.1Backbone=GPT-5.1 Instant2025.10 | 0 | |
| ScholarEval ClaudeBackbone=Claude-4-Sonnet2025.10 | 0 |