Unverified50% confidenceFactExact time
SciResearch-Eval contains 93 held-out tasks, 9 models, and 2,511 episodes in total.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/17/2026
First Seen
Valid until: 2/15/2027
Sources
Related Entities
Related Claims
UnverifiedThese 198 unsolved tasks account for 93% of the message board discussion volume among agents.66% similarUnverifiedThe research team conducted a retrospective ablation analysis across 12 models with a total of 121,680 valid trials, of which 79,853 failed the executability check.65% similarUnverifiedThe test suite consists of 10 benchmarks; most run 1,000 questions each, with HumanEval comprising 164 questions and TruthfulQA comprising 817 questions.63% similarUnverifiedAmong the OSWorld-Verified results tracked by Yutori, of the 111 records annotated with the number of runs, 94 were run only once.62% similarUnverifiedAcross the ten models in the study, a total of 110,764 safely reachable states were explored.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1178922API
curl https://kongchang.com/api/v1/knowledge/claims/1178922MCP
get_claim(id=1178922)