← All models

GPT-4

deprecated by benchmark source
OpenAI · released 2023-03-14 · 2 offers

Context 8K tokens

Top 1 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

#ProviderAdjusted $/task
1Azure

Composite

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

8.9

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Coding: percentile 13AA Intelligence: percentile 22

AA Coding 13.1Coding Agent v1.4 AA Intelligence 6.7AA Agentic Epoch ECI Software ECI DesignArena —/—

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

Benchmark sheet

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

Compare this model →

Agentic

  • GDPval-AA v210189 Elo

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

Coding

  • AA Coding Index1313.1

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

Instruction-following

Knowledge

Reasoning

Science

Missing coverage · 139 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 · 1 offers (Adjusted $/task)

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

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

OpenRouter (1)

Azure
GPT-4 — benchmarks & cost | Benchmark Heaven