Unverified50% confidenceFactExact time
Under the correct-text setting, NitiBench+ ranked 26 models on a test set of 500 held-out samples stratified by domain, and also released an isomorphic validation set for public use.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/3/2026
First Seen
Valid until: 2/1/2027
Sources
Related Entities
Related Claims
UnverifiedThe whatmodel.sh leaderboard collected 22,113 benchmark results from 1,011 sources, covering 987 benchmarks.70% similarUnverifiedThe researchers constructed a benchmark test set called ALIGNMENTFORECASTBENCH, covering more than 5,000 prediction questions, 17 target models, 32 datasets, and 16 failure modes.69% similarUnverifiedThe BTZSC benchmark evaluated dozens of zero-shot classifiers across 22 datasets, covering NLI models, embedding models, and rerankers, with the associated paper published at ICLR 2026.69% similarUnverifiedByteBench包含从真实Replit使用记录中挑选的20个测试场景，未使用合成数据68% similarUnverifiedThe evaluation covered nine text-based scientific benchmarks, sampling 4,531 questions and 100 matched profiles, with 4,488 items completing all five conditions in full.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1130209API
curl https://kongchang.com/api/v1/knowledge/claims/1130209MCP
get_claim(id=1130209)