ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Sonnet 4.5vsGLM-5.2

GLM-5.2 leads 6 of 6 shared benchmarks. GLM-5.2 is 3.1x cheaper per token. GLM-5.2 has the larger context window (1M tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 6
GLM-5.2 leads
Cheaper per token
GLM-5.2
3.1x cheaper, input + output
Larger context
GLM-5.2
1M tokens
Provider uptime (30d)
100% · —
Anthropic · Z.ai
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Context
200K
Max out
64K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
21 · 10 core
GLM-5.2
Z.ai · released 2026-06-24
text
Context
1M
Max out
131K
Input /1M
$1.4
Output /1M
$4.4
Cached /1M
$0.26
Scores
26 · 9 core
Quality

Benchmark matrix

BenchmarkClaude Sonnet 4.5GLM-5.2ΔEdge
Reported by both · 6
GPQA Diamond83.4% 91.9% epoch-8.5 ptGLM-5.2
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epoch29.3% epoch-26.9 ptGLM-5.2
FrontierMath Tiers 1-3 v2 (Epoch AI run)23.9% epoch59.2% epoch-35.3 ptGLM-5.2
OTIS Mock AIME 2024-2025 (Epoch AI run)77.8% epoch86.4% epoch-8.6 ptGLM-5.2
SimpleQA Verified30.7% epoch34.2% epoch-3.5 ptGLM-5.2
SWE-bench Verified (Epoch AI run)71.3% epoch78.7% epoch-7.4 ptGLM-5.2
Only Claude Sonnet 4.5 reports · 14
SWE-bench Verified77.2% not reported
AIME 202584.2% matharenanot reported
Humanity's Last Exam (no tools)17.7% not reported
ARC-AGI-2 (Verified)13.6% not reported
GDPval-AA1276 not reported
Humanity's Last Exam (with tools)33.6% not reported
MCP Atlas43.8% not reported
MMMLU89.5% not reported
MMMU-Pro (no tools)63.4% not reported
MMMU-Pro (with tools)68.9% not reported
OSWorld-Verified61.4% not reported
Tau2-bench Retail86.2% not reported
Tau2-bench Telecom98% not reported
Terminal-Bench 2.051% not reported
Only GLM-5.2 reports · 19
AIME 2026not reported90% matharena
Agents' Last Exam (ALE-CLI)not reported23.8%
AutomationBench v1.0.6not reported26.2%
CyberGymnot reported77.2%
DeepSWE v1.1not reported46.2%
ExploitBenchnot reported24.4%
ExploitGym 2hnot reported29
ExploitGym 6hnot reported39
FrontierSWEnot reported67.5%
GDPval-AA v2not reported1508
HLE (with tools)not reported54.7%
NL2Reponot reported48.9%
PostTrainBenchnot reported31.7%
ProgramBench (Almost Solved)not reported9.5%
SWE-Bench Pronot reported62.1%
SWE-Marathon v1.1not reported19.4%
Terminal-Bench 2.1not reported81%
Terminal-Bench 3.0not reported4.6%
Toolathlon Verifiednot reported59.9%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Sonnet 4.5 minus GLM-5.2 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecClaude Sonnet 4.5GLM-5.2Edge
Context window200K tokens1M tokensGLM-5.2
Max output64K tokens131K tokensGLM-5.2
Input price / 1M$3 $1.4 GLM-5.2
Output price / 1M$15 $4.4 GLM-5.2
Cached input / 1M$0.3 $0.26 GLM-5.2
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$5.8GLM-5.2
Modalitiestext · visiontextClaude Sonnet 4.5
Released2025-09-292026-06-24
Cited benchmark scores2126
Reliability

Provider status

All providers
More matchups

Claude Sonnet 4.5 vs …

More matchups

GLM-5.2 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Sonnet 4.5 and GLM-5.2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.