DeepSeek V4.1 Flash benchmarks leak: beats GPT-5.6 Sol on agentic/coding tasks at $0.14/M input
ChrisGPT · x · 2026-09-10
ChrisGPT reports DeepSeek V4.1 Flash has dropped: a 552B MoE activating 8B params for input and 16B for output, allegedly beating GPT-5.6 Sol and Opus 5 on several agentic/coding benchmarks — CyberGym 88.1 vs 84.5, Automation-Bench 54.8 vs 45.8, DeepSWE 74.2 vs 73.0. Off-peak API pricing is roughly $0.14/M input and $0.56/M output. Unconfirmed officially.
Related event: Leaked DeepSeek V4.1 Benchmarks Point to New 552B Architecture(15 posts)→
More from Models
- DeepSeek V4.1 Flash is actually 748B params, safetensors analysis shows — DistanceSolar1449 · 2026-09-10
- Kimi K3 lands on RunPod: 2.8T params, 1M context, $3/$15 per 1M tokens — Kimi_Moonshot · 2026-09-10
- Dev burns 300M tokens on GLM 5.3 in a week and still has quota left — saibharadwaj · 2026-09-10
- Follow-up: a 3T-parameter model may already exist, scaling issues remain the wildcard — teortaxesTex · 2026-09-10
- Speculation: DeepSeek V4.1 Pro could be a 3.1T-param MoE with 2.6TB disk footprint — teortaxesTex · 2026-09-10
- New Book Teaches Beginners to Build and Fine-Tune Their Own GPT-Style SLMs, With Colab Notebooks — Roger_M_Taylor · 2026-09-10