Claude Opus 5.5vsGLM-5.2

Claude Opus 5.5
GLM-5.2
Specifications
Parameters
744B
Context window
1M1M
API pricing
Input price
$4.00$1.40
Output price
$20.00$4.40
Cached input price
$0.20$0.26
Cheapest input
$0.5625DeepInfra
Cheapest output
$1.80DeepInfra
Benchmarks
Humanity's Last Exam · with tools
67.7%54.7%
Benchmarks
BullshitBench v2
31%
ProgramBench
0%
SWE-Bench Pro
62.1%
DeepSWE 1.1
44%
FrontierCode v1.1 (Main) · main split
54.4%
Next.js Evals
81%
Frontier-Bench v0.1
5.1%
Terminal-Bench 4.0
66.4%
Terminal-Bench 2.1
81%
Terminal-Bench-Science 0.1
58.7%
Humanity's Last Exam · no tools
40.5%
GPQA Diamond
91.2%
OSWorld 2.0
81.8%
AutomationBench
40%
GDPval-AA v2.1
1846
GDPval-AA v2
1514
Chartography · with tools
89%
Overview
CompanyAnthropicZ.ai
Release dateSep 22 2026Jun 16 2026
AccessProprietaryOpen Weight

Other comparisons

Claude Opus 5.5vsGPT-6 AstraGLM-5.2vsGPT-6 AstraClaude Opus 5.5vsGemini 3.8 FlashGLM-5.2vsGemini 3.8 FlashClaude Opus 5.5vsMuse Spark 1.3GLM-5.2vsMuse Spark 1.3Claude Opus 5.5vsGrok 4.7GLM-5.2vsGrok 4.7Claude Opus 5.5vsDeepSeek-V4.1-FlashGLM-5.2vsDeepSeek-V4.1-FlashClaude Opus 5.5vsMistral Medium 3.5GLM-5.2vsMistral Medium 3.5

Frequently asked questions

Claude Opus 5.5 leads GLM-5.2 on 1 of the 1 benchmark they both report (Humanity's Last Exam). GLM-5.2 is cheaper on both input and output: $1.40 vs $4.00 per million input tokens, and $4.40 vs $20.00 per million output tokens. GLM-5.2 shipped 98 days before Claude Opus 5.5, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Opus 5.5) vs 1M (GLM-5.2). Claude Opus 5.5 is proprietary, while GLM-5.2 is open weight.

On Humanity's Last Exam · with tools, Claude Opus 5.5 leads at 67.7% vs GLM-5.2 at 54.7%.