Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Skill Retrieval on BigCodeBench (Recall@1, Recall@10)
Loading...
28.2
Recall@1
Qwen3-32B
18.632
21.116
23.6
26.084
Apr 27, 2026
Recall@1
Recall@10
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall@1
Recall@10
Qwen3-32B
Retrieval Stage=LLM-ba...
2026.04
28.2
79.7
Mistral3.1-24B
Retrieval Stage=LLM-ba...
2026.04
27.7
79.4
Llama-3.3-70B
Retrieval Stage=LLM-ba...
2026.04
27.4
78.6
Qwen3-235B
Retrieval Stage=LLM-ba...
2026.04
27.2
80
Qwen3-4B
Retrieval Stage=LLM-ba...
2026.04
26.3
72.5
BM25
Retrieval Stage=First-...
2026.04
23.6
61.1
Hybrid
Retrieval Stage=First-...
2026.04
23.6
68.4
Llama-3.1-8B
Retrieval Stage=LLM-ba...
2026.04
22.9
68.7
TF-IDF
Retrieval Stage=First-...
2026.04
20.9
60.2
BGE
Retrieval Stage=First-...
2026.04
20.7
62.1
Contriever
Retrieval Stage=First-...
2026.04
19
54.1
Feedback
Search any
task
Search any
task