GLM 5.1

ModelOpen sourceActive

by Z.ai (Zhipu AI) · family “glm”

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on... (description from the OpenRouter listing)

in: textout: textReasoningTool useStructured output

Epoch Capabilities Index

149.9 #50 of 268

90% CI 147.9 – 151.6

Listing ↗

Released

7 Apr 2026

Context window

205K tokens

Max output

131K tokens

Input $ / 1M tokens

$0.96

Output $ / 1M tokens

$3.03

Cached input $ / 1M

$0.18

Each benchmark shown separately with its own source

Benchmark results (13)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
FrontierMath-Tiers-1-3-v2-Private	math	36.8% ±2.9	39%	—	29 Aug 2026	Eval log ↗
ExploitBench	coding	18.1%	25%	—	—	External ↗
ProofBench	math	22.2%	22%	—	—	External ↗
APEX-Agents	agents	40.9%	60%	—	—	External ↗
Chess Puzzles	games	19.0% ±3.9	26%	—	10 Aug 2026	Eval log ↗
SimpleQA Verified	knowledge	34.0% ±1.5	45%	—	27 Aug 2026	Eval log ↗
FrontierMath-Tier-4-2025-07-01-Privatesuperseded	math	12.5% ±4.8	26%	—	12 May 2026	Epoch ↗
FrontierMath-2025-02-28-Privatesuperseded	math	33.4% ±2.8	64%	—	11 May 2026	Epoch ↗
WeirdML	coding	57.1% ±0.0	61%	—	—	External ↗
OTIS Mock AIME 2024-2025	math	93.3% ±3.8	93%	—	10 Aug 2026	Eval log ↗
SimpleBench	reasoning	55.1%	67%	—	—	External ↗
SWE-Bench verified	coding	74.2% ±2.0	89%	—	15 May 2026	Epoch ↗
GPQA diamond	science	89.9% ±2.1	94%	—	10 Aug 2026	Eval 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

8 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.