SShogo Bench

DeepSeek V4.1 Flash vs Kimi K3

Kimi K3 leads DeepSeek V4.1 Flash by 3.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. DeepSeek V4.1 Flash wins 5 and Kimi K3 wins 13 of 19 shared benchmarks. DeepSeek V4.1 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarDeepSeek V4.1 FlashKimi K3
Agentic coding5763
Long-horizon autonomy6265
Knowledge-work agents3942
Computer use4043
Security & context learning5153

Shared benchmarks

BenchmarkDeepSeek V4.1 FlashKimi K3
APEX-Agentsindex39.5%47.8%
ARC-AGI94.5%94.5%
ARC-AGI-272.9%60.4%
Chess Puzzles48.0%37.0%
CritPt14.3%23.4%
DTBench89.9%91.2%
FrontierCode43.9%44.2%
FrontierMath Tier 426.8%39.0%
FrontierMath Tiers 1-367.4%72.2%
GPQA Diamond89.8%93.1%
LMCA47.0%52.7%
MirrorCode64.4%54.4%
OTIS Mock AIME98.3%97.2%
ProofBench54.0%87.0%
SciCode51.9%59.5%
SimpleBench66.7%60.7%
SimpleQA Verified42.9%50.6%
WebDev Arena16141674
WeirdML v35.9%7.5%

Specs and price

DeepSeek V4.1 FlashKimi K3
Agent Index51.2 (#35)54.9 (#26)
Agent $/M$0.12$1.39
Input / output $/M$0.30 / $1.20$3.00 / $15.00
Context1M1M
ReleasedSep 10, 2026Jul 16, 2026
WeightsOpenOpen
API hosts3929

Don’t pick one. Route.

Shogo can run DeepSeek V4.1 Flash and Kimi K3 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo