Claude Sonnet 4.5 vs GLM-4.6

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Claude Sonnet 4.5

Anthropic · Sep 2025

65.5

The model that made 30-hour autonomous coding sessions real — 77.2% SWE-bench Verified and a 1M-token context beta at $3/$15.

GLM-4.6

Z.ai (Zhipu) · Sep 2025

63.9

The budget coding-agent favorite of late 2025 — near-Sonnet coding utility with MIT weights and a $3/month plan.

The verdict

Claude Sonnet 4.5 wins 4 of the 5 benchmarks these models share, against 1 for GLM-4.6. On price the gap is dramatic: GLM-4.6 works out roughly 6.0x cheaper per blended million tokens. And GLM-4.6 is open-weights (MIT), so it can be self-hosted — a structural advantage if data control or vendor independence matters.

Benchmark head-to-head 41

SWE-bench Verified
77.2%68%
Claude Sonnet 4.5GLM-4.6
GPQA Diamond
83.4%~81%
Claude Sonnet 4.5GLM-4.6
AIME 2025
87%~93.9%
Claude Sonnet 4.5GLM-4.6
HLE
~17.3%~17.2%
Claude Sonnet 4.5GLM-4.6
Terminal-Bench
50%40.5%
Claude Sonnet 4.5GLM-4.6

Specs & pricing

Claude Sonnet 4.5GLM-4.6
modhub Index65.563.9
Input price / 1M$3$0.6
Output price / 1M$15$2.2
Context window200K200K
Max output64K128K
Open weightsnoyes (MIT)
Reasoning modelyesyes
Multimodal inputtext, imagetext
Knowledge cutoffJan 2025Jul 2025
ReleasedSep 2025Sep 2025
Example monthly cost*$52.50$9.30

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Claude Sonnet 4.5 or GLM-4.6?
Claude Sonnet 4.5 wins 4 of the 5 benchmarks these models share, against 1 for GLM-4.6. On price the gap is dramatic: GLM-4.6 works out roughly 6.0x cheaper per blended million tokens. And GLM-4.6 is open-weights (MIT), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
Which is cheaper, Claude Sonnet 4.5 or GLM-4.6?
Claude Sonnet 4.5 costs $3/$15 per million input/output tokens, while GLM-4.6 costs $0.6/$2.2. For a typical workload of 10M input and 1.5M output tokens per month, that's $52.50 versus $9.30.
Which model is better for coding, Claude Sonnet 4.5 or GLM-4.6?
On SWE-bench Verified — the standard agentic-coding benchmark — Claude Sonnet 4.5 scores 77.2% versus 68% for GLM-4.6, making Claude Sonnet 4.5 the stronger pick for coding agents.

More comparisons