RAG
by SWE-agent
7.0
best score
7.0%
Best Score
verified
Best Leaderboard
6
Models Used
Yes
Open Source
Score History
| Entry | Score |
|---|---|
| RAG + GPT 4o (2024-08-06) | 6.0% |
| RAG + Claude 3.5 Sonnet | 5.0% |
| HyperAgent | 25.3% |
| RAG + Claude 3 Opus | 3.8% |
| RAG + GPT 4 (1106) | 1.3% |
| RAG + Claude 3 Opus | 7.0% |
| RAG + GPT 4 (1106) | 2.8% |
| RAG + Claude 3 Opus | 4.3% |
| RAG + GPT 4 (1106) | 2.7% |
| RAG + Claude 2 | 2.0% |
| RAG + SWE-Llama 13B | 0.7% |
| RAG + SWE-Llama 7B | 0.7% |
| RAG + ChatGPT 3.5 | 0.2% |
| RAG + Claude 2 | 4.4% |
| RAG + SWE-Llama 7B | 1.4% |
| RAG + SWE-Llama 13B | 1.2% |
| RAG + ChatGPT 3.5 | 0.4% |
| RAG + Claude 2 | 3.0% |
| RAG + SWE-Llama 7B | 1.3% |
| RAG + SWE-Llama 13B | 1.0% |
| RAG + ChatGPT 3.5 | 0.3% |