Unverified50% confidenceBenchmarkExact time
Unlimited OCR 2 scored 77.1 on MarathonDocBench.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/27/2026
First Seen
Valid until: 1/25/2027
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.59% similarUnverifiedWith DeepSeek V4 Pro as the backbone, SwarmRSI achieves an average score of 74.2 on OpenProblems, exceeding the previous SOTA of 67.1.53% similarUnverifiedOn the WildSongBench (WSB) benchmark, YuE2 achieved a SongBench global average score of 6.73, the highest among all public baselines at the time of the report's release; with the best-of-8 strategy the score rose to 6.96, the highest mean observed among all evaluated systems, including commercial systems.52% similarUnverifiedDeepSeek V4.1 claims to achieve 74 on SWE, but the blogger found that this was the best result cherry-picked from multiple tests, with open code testing at 65 and PI testing at 66.51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102917API
curl https://kongchang.com/api/v1/knowledge/claims/1102917MCP
get_claim(id=1102917)