SShogo Bench

DeepSeek V4.1 Flash vs DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 leads DeepSeek V4.1 Flash by 6.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. DeepSeek V4.1 Flash wins 2 and DeepSeek V4.1 Flash 1017 wins 9 of 12 shared benchmarks. DeepSeek V4.1 Flash 1017 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarDeepSeek V4.1 FlashDeepSeek V4.1 Flash 1017
Agentic coding5763
Long-horizon autonomy6266
Knowledge-work agents3949
Computer use4045
Security & context learning5154

Shared benchmarks

BenchmarkDeepSeek V4.1 FlashDeepSeek V4.1 Flash 1017
APEX-Agentsindex39.5%69.8%
ARC-AGI94.5%94.5%
ARC-AGI-272.9%78.1%
Chess Puzzles48.0%46.0%
CritPt14.3%24.0%
FrontierMath Tier 426.8%46.3%
FrontierMath Tiers 1-367.4%71.2%
GPQA Diamond89.8%93.2%
OTIS Mock AIME98.3%99.4%
SciCode51.9%55.9%
SimpleQA Verified42.9%42.5%
WeirdML v35.9%9.1%

Specs and price

DeepSeek V4.1 FlashDeepSeek V4.1 Flash 1017
Agent Index51.2 (#35)57.6 (#17)
Agent $/M$0.12$0.050
Input / output $/M$0.30 / $1.20$0.15 / $0.60
Context1M1M
ReleasedSep 10, 2026Oct 17, 2026
WeightsOpenOpen
API hosts3951

Don’t pick one. Route.

Shogo can run DeepSeek V4.1 Flash and DeepSeek V4.1 Flash 1017 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo