| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MTEB Code Retrieval Average (val) | nDCG@574 | 24 | 1mo ago | ||
| FreshStack (val) | nDCG@543.8 | 24 | 1mo ago | ||
| DS10K (val) | Policy Optimization | nDCG@563.8 | 24 | 1mo ago | |
| MBPP (val) | nDCG@592 | 24 | 1mo ago | ||
| HumanEval (val) | Policy Optimization | nDCG@598.5 | 24 | 1mo ago | |
| MTEB Code | qwen3-embed-4B | nDCG@1080.07 | 21 | 20d ago | |
| CSN-Python Non-target Queries (test) | VenomRACG | MRR0.669 | 19 | 3mo ago | |
| CSN-Python Target Queries (test) | VenomRACG | ASR@117.64 | 18 | 3mo ago | |
| CodeSearch | SANTA | MRR47.5 | 16 | 3mo ago | |
| MTEB Code (test) | CodeR-all-1.5B | Apps Score98.1 | 12 | 2mo ago | |
| DupStackMath | EuroBERT | nDCG@1048.3 | 10 | 1d ago | |
| Adv | SANTA (Hard Negative) | MRR48.6 | 9 | 3mo ago | |
| COSQA Code | ProRank | NDCG@1032.05 | 8 | 1mo ago | |
| MTEB Code v1 (test) | Gemini Embedding 2 | Mean Score84 | 2 | 7d ago | |
| CodeSearch (test) | - | MRR- | 0 | 3mo ago |