← All models

GLM-4.7 (Reasoning)

open weightsdeprecated by benchmark source
Z.ai · released 2025-12-22 · 7 offers

Context 200K tokens

Top 5 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.

#ProviderAdjusted $/task
1DeepInfravia OpenRouter — Price via OpenRouter: OpenRouter's price for DeepInfra's endpoint (https://openrouter.ai/z-ai/glm-4.7/providers), collected 2026-11-22.
2Venicevia OpenRouter — Price via OpenRouter: OpenRouter's price for Venice's endpoint (https://openrouter.ai/z-ai/glm-4.7/providers), collected 2026-11-22.
3Mancer 2via OpenRouter — Price via OpenRouter: OpenRouter's price for Mancer 2's endpoint (https://openrouter.ai/z-ai/glm-4.7/providers), collected 2026-11-22.
4Google Vertex AIdirect — Direct price: Google Vertex AI's own price list (https://cloud.google.com/vertex-ai/generative-ai/pricing), collected 2026-11-22.
5AWS Bedrockdirect — Direct price: AWS Bedrock's own price list (https://aws.amazon.com/bedrock/pricing/), collected 2026-11-22.

Composite

4 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one

15.7

includes −10.5 for its Benchmaxxing signal (from 26.1; why, switch off in Options)

Benchmaxxing signal +10.5, medium Benchmaxxing tag, uncertain: Based on only 6 comparisons — treat this tag as uncertain · medium report →Based on only 6 comparisons — treat this tag as uncertain.

AA Coding v4.xCoding Agent v1.4AA Intelligence (est.)AA AgenticEpoch ECISoftware ECIDesignArenaAA Coding v4.x: percentile 52AA Intelligence (est.): percentile 69Epoch ECI: percentile 20DesignArena: percentile 11

AA Coding v4.x 45.3Coding Agent v1.4 —AA Intelligence (est.) 11.7AA Agentic —Epoch ECI 143.3Software ECI —DesignArena —/1028

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

Benchmark sheet

16 of 320 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Composite attachments (used in the score, not counted as exact benchmarks):
  • Epoch ECI · attached
  • DesignArena Full-Stack · attached
Compare this model →

Agentic

  • GDPval-AA v2571,096 Elo

    GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.

  • Terminal-Bench Hard (AA)7531.8%

    Terminal-Bench Hard (AA) pinned revision 74221fb → · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.

  • Terminal-Bench v2.1 (AA)4645.3%

    Terminal-Bench v2.1 (AA) v2.1 → · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.

  • τ²-Bench Airline (OpenRouter run)6173.0%

    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.)

Coding

  • AA Coding Index v4.x · frozen 2026-10-275245.3

    AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).

  • DesignArena Full-Stack131,028 Elo

    DesignArena Full-Stack published 2026-11-22 → · Published board — Published Elo. Exact source attachment is retained; fewer than 200 battles excludes a row from radar normalization and anomaly peers.

Efficiency

Instruction-following

Knowledge

Long-context

  • AA-LCR v1.16771.0%

    AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.

Math

  • AIME 2025 (AA)9795.0%

    AIME 2025 (AA) v2025 → · Published board — Advanced mathematical problem solving on AIME I and II 2025.

Science

Tool-use

  • τ²-Bench Telecom (AA)9695.9%

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

  • τ³-Banking (AA) v1.0.13612.2%

    τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.

Missing coverage · 304 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.

Variants / reasoning settings

Artificial Analysis snapshot 2026-11-04 · Intelligence Index v5.0 (est. = estimated from v4, not measured) · Coding Index v4.x frozen 2026-10-27 · Data: Artificial Analysis · Data: Epoch AI (CC BY)

VariantAA CodingAA Intelligence
GLM-4.7 (Reasoning)45.311.7est.
GLM-4.7 (Non-reasoning)—6.3est.
Token offers by platform · 5 offers (Adjusted $/task)

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

5 offers within the active global filters, 2 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.

OpenRouter (3)

Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/z-ai/glm-4.7/providers, collected 2026-11-22.

DeepInfra
Venice
Mancer 2

Google Vertex AI (1)

Direct prices from Google Vertex AI's own price list. Source: cloud.google.com/vertex-ai/generative-ai/pricing, collected 2026-11-22.

Google Vertex AI

AWS Bedrock (1)

Direct prices from AWS Bedrock's own price list. Source: aws.amazon.com/bedrock/pricing/, collected 2026-11-22.

AWS Bedrock
GLM-4.7 (Reasoning) — benchmarks & cost | Benchmark Heaven