DeepSeek V4.1F tops Chinese models on FrontierMath Tier 4 at 46%
teortaxesTex · x · 2026-10-26
teortaxesTex notes that DeepSeek V4.1F-1017 is now the strongest Chinese model on Epoch's FrontierMath Tier 4 (v2) leaderboard, scoring 46% — on par with Qwen 3.8 Max (Aug 2) and Haiku 5.5.
Earlier DeepSeek versions scored far lower: V4-Flash 0731 at 24%, and both V4-Pro-0813 and V4.1-Flash (0910) at 27%. The author concludes DeepSeek has resumed hill-climbing on math. The leaderboard screenshots show 77 models tested, with frontier US models like GPT-6.1 Sol nearing 100%.
Related event: DeepSeek V4.1F Tops FrontierMath Tier 4 as Best Chinese Model(2 posts)→
More from Models
- DeepSeek V4.1 Flash with OpenCode Go: cheap unlimited coding agent with Opus validating results — haider1 · 2026-10-26
- yacine claims OpenAI models have allowed 'borderline and dangerous' tasks since codex 5.4 — yacineMTB · 2026-10-26
- Block unveils Dessa, a full-duplex speech model trained only on human conversation — daluoseo · 2026-10-26
- Casado slams Claude's safety classifier for flagging 'fetching my own documents' as reasoning extraction — AccBalanced · 2026-10-26
- Yacine MTB: DeepSeek is 'undoubtedly' a frontier model — yacineMTB · 2026-10-26
- Single-neuron steering: injecting a "joyful neuron" visibly alters a model's self-description — Sauers_ · 2026-10-26