GLM-4.5-Air

open weightsdeprecated by benchmark source

Z.ai · released 2025-07-28 · 3 offers

Context 128K tokens

Top 3 cheapest providers (Adjusted $/task)

The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.

Within the active global provider, residency and confidentiality filters.

#	Provider	Platform	Raw input $/1M	Raw output $/1M
1	Novita	OpenRouter	$0.130	$0.850
2	Z.AI	OpenRouter	$0.200	$1.10
3	SiliconFlow	OpenRouter	$0.140	$0.860

1 of 7 inputs6 radar axes: DesignArena's two boards share one

19.3

dominance-adjusted from 23.3: a better-measured model that is at least as good on each of these inputs ranks above it

AA Coding —Coding Agent v1.4 —AA Intelligence 11.1AA Agentic —Epoch ECI —Software ECI —DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

18 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Terminal-Bench Hard (AA)6020.5%2026-09-10
Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
τ²-Bench Airline (OpenRouter run)5170.9%2026-09-15
τ²-Bench Airline (OpenRouter run) published 2026-09-15 ↗ · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)

GSO software optimization, Opt@1 (UC Berkeley) vopt1-102112.9%2026-09-16
GSO software optimization, Opt@1 (UC Berkeley) vopt1-102 ↗ · OpenHands — An agent gets a real codebase and a performance test and must make the code as fast as an expert developer's optimization; 102 tasks across 10 codebases and 5 languages.

GPQA Diamond (OpenRouter run) — measured cost per task63$0.0132026-09-15
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
τ²-Bench Airline (OpenRouter run) — measured cost per task91$0.0142026-09-15
τ²-Bench Airline (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running τ²-Bench Airline for this configuration.

IFBench (AA single-turn)3237.6%2026-09-10
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.

Humanity's Last Exam (AA text-only)457.0%2026-09-10
Humanity's Last Exam (AA text-only) published 2026-09-10 ↗ · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index17-61.52026-09-10
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt7433.32026-09-10
UGI NatInt published 2026-09-10 ↗ · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.

AA-LCR v1.14546.7%2026-09-10
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

AIME 2025 (AA) v20257780.7%2026-09-10
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.

AA Intelligence Index4811.12026-09-19
AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.

CritPt (AA)240.0%2026-09-10
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)5473.3%2026-09-10
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)2364.7%2026-09-15
GPQA Diamond (OpenRouter run) published 2026-09-15 ↗ · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)

τ²-Bench Telecom (AA)5046.5%2026-09-10
τ²-Bench Telecom (AA) published 2026-09-10 ↗ · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.

UGI Willingness101.802026-09-10
UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI5630.62026-09-10
UGI published 2026-09-10 ↗ · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.

UGI Writing8442.02026-09-10
UGI Writing published 2026-09-10 ↗ · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.

Missing coverage · 126 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Token offers by platform · 3 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

3 offers within the active global filters; “—” means the catalog is active but no public token price is available.