SShogo Bench

GLM-5.3-Flash vs GPT-6 Sol

GPT-6 Sol leads GLM-5.3-Flash by 15.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GLM-5.3-Flash wins 0 and GPT-6 Sol wins 13 of 13 shared benchmarks. GLM-5.3-Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGLM-5.3-FlashGPT-6 Sol
Agentic coding5472
Long-horizon autonomy5776
Knowledge-work agents4048
Computer use3454
Security & context learning4759

Shared benchmarks

BenchmarkGLM-5.3-FlashGPT-6 Sol
APEX-Agentsindex52.8%54.3%
ARC-AGI91.0%95.5%
ARC-AGI-265.8%89.6%
Chess Puzzles21.0%56.0%
CritPt15.4%30.9%
FrontierCode31.8%49.3%
FrontierMath Tier 417.1%90.0%
FrontierMath Tiers 1-355.8%89.8%
GPQA Diamond90.2%94.3%
OTIS Mock AIME93.9%100.0%
ProofBench21.0%83.0%
SciCode51.6%57.6%
WebDev Arena16071689

Specs and price

GLM-5.3-FlashGPT-6 Sol
Agent Index48.3 (#38)63.6 (#13)
Agent $/M$0.16$0.92
Input / output $/M$0.30 / $1.05$2.00 / $10.00
Context1M1.1M
ReleasedSep 18, 2026Sep 22, 2026
WeightsOpenClosed
API hosts425

Don’t pick one. Route.

Shogo can run GLM-5.3-Flash and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo