Skip to content

GLM 4.7

ModelOpen sourceActive
by Z.ai (Zhipu AI) · family “glm”

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while... (description from the OpenRouter listing)

in: textout: textReasoningTool useStructured output
Epoch Capabilities Index
143.5 #90 of 268
90% CI 141.0 – 145.5
Listing ↗
Released
22 Dec 2025
Context window
205K tokens
Max output
131K tokens
Input $ / 1M tokens
$0.60
Output $ / 1M tokens
$2.20
Cached input $ / 1M
$0.11
Each benchmark shown separately with its own source

Benchmark results (7)

BenchmarkDomainScorevs best recordedSettingRunSource
ProofBenchmath6.0%
6%
——External ↗
Chess Puzzlesgames6.0% ±1.6
8%
—29 Jan 2026Eval log ↗
SimpleQA Verifiedknowledge32.2% ±1.5
43%
—27 Aug 2026Eval log ↗
Terminal Benchagents33.4% ±2.8
39%
agent: Terminus 222 Dec 2025External ↗
OTIS Mock AIME 2024-2025math83.3% ±4.8
83%
—29 Jan 2026Eval log ↗
SimpleBenchreasoning47.7%
58%
——External ↗
GPQA diamondscience83.3% ±2.4
87%
—29 Jan 2026Eval log ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

10 recorded prices on 7 Jan 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 11h ago. Steps show when the price changed.

Events