Claude 2vsGLM-5.3-Flash

Claude 2
GLM-5.3-Flash
Specifications
Parameters
320B
Context window
100k1M
API pricing
Cheapest input
$0.075DeepInfra
Cheapest output
$0.25DeepInfra
Benchmarks
DeepSWE 1.1
63.4%
NL2Repo-Bench
56.3%
HumanEval
71.2%
Terminal-Bench 2.1
84.3%
Toolathlon-Verified
78.4%
Humanity's Last Exam · with tools
55.3%
MMLU
78.5%
GSM8K
88%
Agent's Last Exam · pass@1
26.3%
AutomationBench
48.8%
GDPval-AA v2
1773
CharXiv Reasoning · with tools
89.4%
Chartography · with tools
78%
OfficeQA Pro
62.4%
MVBench
77.8%
MMVU
80.5%
BabyVision
53.4%
threejseval
1502
Overview
CompanyAnthropicZ.ai
Release dateJul 11 2023Aug 26 2026
AccessProprietaryOpen Weight

Other comparisons

Claude 2vsGPT-6 AstraGLM-5.3-FlashvsGPT-6 AstraClaude 2vsGemini 3.8 FlashGLM-5.3-FlashvsGemini 3.8 FlashClaude 2vsMuse Spark 1.3GLM-5.3-FlashvsMuse Spark 1.3Claude 2vsGrok 4.6GLM-5.3-FlashvsGrok 4.6Claude 2vsDeepSeek-V4.1-FlashGLM-5.3-FlashvsDeepSeek-V4.1-FlashClaude 2vsMistral Medium 3.5GLM-5.3-FlashvsMistral Medium 3.5

Frequently asked questions

Claude 2 and GLM-5.3-Flash don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Claude 2 shipped 1142 days before GLM-5.3-Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude 2) vs 1M (GLM-5.3-Flash). Claude 2 is proprietary, while GLM-5.3-Flash is open weight.

Direct benchmark comparisons are unavailable — Claude 2 and GLM-5.3-Flash don't publish scores on any of the same benchmarks.