LLM Reference

Claude 3.7 Sonnet vs GLM-5

Claude 3.7 Sonnet (2024) and GLM-5 (2026) are frontier-tier reasoning models from Anthropic and Zhipu AI. Claude 3.7 Sonnet ships a 200k-token context window, while GLM-5 ships a 200k-token context window. On MMLU PRO, GLM-5 leads by 5.7 pts. On pricing, GLM-5 costs $0.60/1M input tokens versus $3/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

GLM-5 is ~400% cheaper at $0.60/1M; pay for Claude 3.7 Sonnet only for coding workflow support.

Decision scorecard

Local evidence first
SignalClaude 3.7 SonnetGLM-5
Best forreasoning-heavy apps, multimodal apps, and tool-calling agentsreasoning-heavy apps, tool-calling agents, and provider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window200k200k
Cheapest output$15/1M tokens$2.08/1M tokens
Provider routes6 tracked7 tracked
Shared benchmarks3 sharedMMLU PRO leader

Decision tradeoffs

Choose Claude 3.7 Sonnet when...
  • Claude 3.7 Sonnet uniquely exposes Vision, Multimodal, and Code execution in local model data.
  • Local decision data tags Claude 3.7 Sonnet for Coding, RAG, and Agents.
Choose GLM-5 when...
  • GLM-5 holds a shared-benchmark lead on MMLU PRO, ahead by 5.7 points.
  • GLM-5 has the lower cheapest tracked output price at $2.08/1M tokens.
  • GLM-5 has broader tracked provider coverage for fallback and route flexibility.
  • Local decision data tags GLM-5 for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate GLM-5

Claude 3.7 Sonnet

$6,150

Cheapest tracked route/tier: GCP Vertex AI

GLM-5

$1,000

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $5,150. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Claude 3.7 Sonnet -> GLM-5
  • Provider overlap exists on OpenRouter and GCP Vertex AI; start route-level A/B tests there.
  • GLM-5 is $12.92/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Vision, Multimodal, and Code execution before moving production traffic.
GLM-5 -> Claude 3.7 Sonnet
  • Provider overlap exists on GCP Vertex AI and OpenRouter; start route-level A/B tests there.
  • Claude 3.7 Sonnet is $12.92/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Claude 3.7 Sonnet adds Vision, Multimodal, and Code execution in local capability data.

Specs

Specification
Released2024-03-042026-02-11
Context window200k200k
Parameters744B total, 40B active
ArchitectureDecoder OnlyMixture of Experts
LicenseProprietaryMITOSI-approved
OpennessProprietaryOpen source
WeightsNot releasedAvailable
CodeUnknownUnknown
Commercial useCommercial use: conditionalCommercial use: permitted
Knowledge cutoff2024-112025-11

Pricing and availability

Pricing attributeClaude 3.7 SonnetGLM-5
Input price$3/1M tokens$0.60/1M tokens
Output price$15/1M tokens$2.08/1M tokens
Providers

Capabilities

CapabilityClaude 3.7 SonnetGLM-5
VisionYesNo
MultimodalYesNo
ReasoningYesYes
JSON / Tool useYesYes
Structured outputsYesYes
Code executionYesNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkClaude 3.7 SonnetGLM-5
MMLU PRO80.386.0
SWE-bench Verified70.377.8
LiveCodeBench68.981.9

Continue comparing

Last reviewed: 2026-07-26. Data sourced from public model cards and provider documentation.