SShogo Bench

DeepSeek V4.1 Flash 1017 vs GPT-5.4

DeepSeek V4.1 Flash 1017 leads GPT-5.4 by 6.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. DeepSeek V4.1 Flash 1017 wins 5 and GPT-5.4 wins 6 of 11 shared benchmarks. DeepSeek V4.1 Flash 1017 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarDeepSeek V4.1 Flash 1017GPT-5.4
Agentic coding6357
Long-horizon autonomy6661
Knowledge-work agents4940
Computer use4542
Security & context learning5454

Shared benchmarks

BenchmarkDeepSeek V4.1 Flash 1017GPT-5.4
APEX-Agentsindex69.8%52.4%
ARC-AGI94.5%93.7%
ARC-AGI-278.1%74.0%
Chess Puzzles46.0%48.0%
CritPt24.0%23.4%
FrontierMath Tier 446.3%49.0%
FrontierMath Tiers 1-371.2%78.6%
GPQA Diamond93.2%93.3%
OTIS Mock AIME99.4%97.8%
SciCode55.9%56.6%
SimpleQA Verified42.5%45.1%

Specs and price

DeepSeek V4.1 Flash 1017GPT-5.4
Agent Index57.6 (#17)51.6 (#33)
Agent $/M$0.050$1.27
Input / output $/M$0.15 / $0.60$2.50 / $15.00
Context1M1.1M
ReleasedOct 17, 2026Mar 5, 2026
WeightsOpenClosed
API hosts514

Don’t pick one. Route.

Shogo can run DeepSeek V4.1 Flash 1017 and GPT-5.4 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo