Expired65% confidenceBenchmarkExact time
At the time of observation, MiMo-V2.6 Pro's DeepSWE v1.1 score was 62.24 and MiMo-V2.6 Flash's was 60.77.
3
Sources
65%
Confidence
Short-term (~14 days)
Relevance
9/17/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/1/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe live-stream page simultaneously trains two models, MiMo-V2.6 Pro and MiMo-V2.6 Flash.77% similarVerifiedV4.1 Flash surpassed Opus 5 on the DeepSWE benchmark by a narrow margin of 0.2 points.74% similarUnverifiedThe release party claimed that DeepSeek-V4.1-Flash outperforms Opus 5 and GPT-5.6 Sol on three benchmarks: DeepSWE, CyberGym, and Automation Bench.68% similarUnverifiedV4.1 Flash scored 74.2 on the SWE software engineering benchmark, 90.6 on the terminal benchmark, and 3,471 points on Tonka Forces evaluation (vs. 3,348 for VS Pro).66% similarUnverifiedDeepSeek-V4.1-Flash adopts a MoE (Mixture of Experts) backbone architecture with 552B parameters.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928558API
curl https://kongchang.com/api/v1/knowledge/claims/928558MCP
get_claim(id=928558)