SShogo Bench

DeepSeek V4.1 Flash 1017 vs GLM-5.3-Flash

DeepSeek V4.1 Flash 1017 leads GLM-5.3-Flash by 9.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. DeepSeek V4.1 Flash 1017 wins 11 and GLM-5.3-Flash wins 0 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 1017GLM-5.3-Flash
Agentic coding6354
Long-horizon autonomy6657
Knowledge-work agents4940
Computer use4534
Security & context learning5447

Shared benchmarks

BenchmarkDeepSeek V4.1 Flash 1017GLM-5.3-Flash
APEX-Agentsindex69.8%52.8%
CursorBenchindex47.7%36.8%
ARC-AGI94.5%91.0%
ARC-AGI-278.1%65.8%
Chess Puzzles46.0%21.0%
CritPt24.0%15.4%
FrontierMath Tier 446.3%17.1%
FrontierMath Tiers 1-371.2%55.8%
GPQA Diamond93.2%90.2%
OTIS Mock AIME99.4%93.9%
SciCode55.9%51.6%

Specs and price

DeepSeek V4.1 Flash 1017GLM-5.3-Flash
Agent Index57.6 (#17)48.3 (#38)
Agent $/M$0.050$0.16
Input / output $/M$0.15 / $0.60$0.30 / $1.05
Context1M1M
ReleasedOct 17, 2026Sep 18, 2026
WeightsOpenOpen
API hosts5142

Don’t pick one. Route.

Shogo can run DeepSeek V4.1 Flash 1017 and GLM-5.3-Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo