SShogo Bench

Claude Sonnet 5.5 vs GLM-5.3-Flash

Claude Sonnet 5.5 leads GLM-5.3-Flash by 20.7 points on the Shogo Agent Index. Claude Sonnet 5.5 wins 15 and GLM-5.3-Flash wins 0 of 15 shared benchmarks. GLM-5.3-Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Sonnet 5.5GLM-5.3-Flash
Agentic coding7954
Long-horizon autonomy7557
Knowledge-work agents5740
Computer use6134
Security & context learning6147

Shared benchmarks

BenchmarkClaude Sonnet 5.5GLM-5.3-Flash
APEX-Agentsindex75.5%52.8%
FrontierSWEindex61.9%18.1%
CursorBenchindex55.5%36.8%
ARC-AGI96.5%91.0%
ARC-AGI-283.9%65.8%
Chess Puzzles59.0%21.0%
CritPt31.4%15.4%
FrontierCode52.1%31.8%
FrontierMath Tier 480.5%17.1%
FrontierMath Tiers 1-388.8%55.8%
GPQA Diamond95.6%90.2%
OTIS Mock AIME100.0%93.9%
ProofBench100.0%21.0%
SciCode61.0%51.6%
WebDev Arena17861607

Specs and price

Claude Sonnet 5.5GLM-5.3-Flash
Agent Index69 (#9)48.3 (#38)
Agent $/M$0.84$0.16
Input / output $/M$2.00 / $10.00$0.30 / $1.05
Context1M1M
ReleasedSep 28, 2026Sep 18, 2026
WeightsClosedOpen
API hosts542

Don’t pick one. Route.

Shogo can run Claude Sonnet 5.5 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