Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Skill Retrieval on TheoremQA
Loading...
77.4
nDCG@1
Qwen3-32B
39.96
49.68
59.4
69.12
Apr 27, 2026
nDCG@1
nDCG@10
Updated 1mo ago
Evaluation Results
Method
Method
Links
nDCG@1
nDCG@10
Qwen3-32B
Retrieval Stage=Rerank...
2026.04
77.4
83.5
Llama-3.3-70B
Retrieval Stage=Rerank...
2026.04
76
82.8
Qwen3-235B
Retrieval Stage=Rerank...
2026.04
75.4
83.1
Mistral3.1-24B
Retrieval Stage=Rerank...
2026.04
74.2
81.9
Qwen3-4B
Retrieval Stage=Rerank...
2026.04
69.5
79
BGE
Retrieval Stage=First-...
2026.04
66.8
75.9
Llama-3.1-8B
Retrieval Stage=Rerank...
2026.04
58.8
71.5
BM25
Retrieval Stage=First-...
2026.04
57.2
69.2
Hybrid
Retrieval Stage=First-...
2026.04
57.2
75.3
Contriever
Retrieval Stage=First-...
2026.04
52.1
63.8
TF-IDF
Retrieval Stage=First-...
2026.04
41.4
54.4
Feedback
Search any
task
Search any
task