Expired50% confidenceBenchmarkExact time
AIBuildAI-2.5 ranked first on MLE-Bench, achieving a medal rate of 73.3%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/23/2026
First Seen
Valid until: 10/7/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe same DeepSeek v1.1 model scored between 69.8% and 74.2% on Terminal Bench 2.0 under different harnesses.57% similarUnverifiedThe flagship Soul achieved a score of 91.9% on the Terminal Bench 2.1 benchmark.57% similarUnverifiedHaiku 4.5 scored 73.3% on SWE Bench, slightly higher than Sonnet 4 and approaching the level of GPT-5 Codex.57% similarUnverifiedThe official figures show that Nex-N2 Pro scored 58.8 on SWE Bench Pro and 75.3 on Terminal Bench.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942893API
curl https://kongchang.com/api/v1/knowledge/claims/942893MCP
get_claim(id=942893)