ModelsCompareBest forBenchmarksStatusPricingAPI

GLM-5.3-Flash

Z.ai·Pending·Released 2026-09-16textvision
Context1,000k
Max output131.072k
Input / 1M$0.15 ↗
Output / 1M$0.5 ↗
Cached in$0.03
Benchmarks19

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

FrontierMath Tier 4 v2 (Epoch AI run)#31/4417.1% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#29/5955.8% ↗
GPQA Diamond (Epoch AI run)#27/7790.2% ↗
OTIS Mock AIME 2024-2025 (Epoch AI run)#26/7693.9% ↗
Agents' Last Exam (ALE-CLI)#2/326.3% ↗
AutomationBench v1.0.6#1/348.8% ↗
BabyVision#4/453.4% ↗
Chartography (with tools)78% ↗
CharXiv Reasoning (with tools)89.4% ↗
DeepSWE v1.1#10/1363.4% ↗
GDPval-AA v2#3/71773 ↗
HLE (with tools)#2/455.3% ↗
MMVU#2/280.5% ↗
MVBench77.8% ↗
NL2Repo#2/456.3% ↗
OfficeQA Pro#2/262.4% ↗
Terminal-Bench 2.1#6/1784.3% ↗
Toolathlon Verified#1/478.4% ↗
LMArena Elo#5/621471.9 ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from Z.ai

GLM-5.3GLM-5.2GLM-5GLM-4.7-FlashXGLM-5.1GLM-5-Turbo

Access GLM-5.3-Flash and every other model through one endpoint with automatic failover: Respan gateway.