Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

GPT-4

OpenAIReleased Mar 14, 2023Current

Score basis

GPT-4 is behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited1 capability
  1. Factuality−32.5%2 of 4
Not rated9 capabilities

Too few results yet to rate Reasoning, Coding, Agentic, Safety, Long Context, Math, Multimodal, Multilingual or Instruction Following.

Price

$30.00input$60.00outputper million tokens

From Artificial Analysis · 2 providers tracked · All prices

Costs more than 98% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

48results on30benchmarks

  • 30 independently verified
  • 8 aggregator
  • 6 vendor-reported
  • 4 cross-referenced

From 14 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputs

As listed by OpenRouter

Research

164 papers reference GPT-4

GPT-4 benchmark results

48 results on 30 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

LimitedFull factuality ranking

32.5% behind the leader2 of 4 ranked benchmarks measured

Reasoning

Not enough dataFull reasoning ranking

0 of 6 ranked benchmarks measured

Coding

Not enough dataFull coding ranking

0 of 10 ranked benchmarks measured

Show 1 more coding resultHide 1 coding result

Agentic

Not enough dataFull agentic ranking

0 of 7 ranked benchmarks measured

Instruction Following

Not enough dataFull instruction following ranking

0 of 3 ranked benchmarks measured

Show 2 more instruction following resultsHide 2 instruction following results

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 28 more resultsHide 28 results

GPT-4: common questions

Who makes GPT-4?

GPT-4 is made by OpenAI.

When was GPT-4 released?

GPT-4 was released on Mar 14, 2023, according to Artificial Analysis.

What is GPT-4 good at?

GPT-4 is behind the leaders in factuality. Too few results yet to rate reasoning, coding, agentic tasks, safety, long context, math, multimodal tasks, multilingual tasks, or instruction following.

How much does GPT-4 cost?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens, according to Artificial Analysis. We track its price at 2 providers. At a mix of three input tokens to one output token, it costs more than 98% of the 330 priced models we track.

How many benchmarks has GPT-4 been tested on?

We track 48 results for GPT-4 on 30 benchmarks from 14 sources, 30 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does GPT-4 support?

OpenRouter lists tool calling and structured outputs for GPT-4.

About this record

Where GPT-4's numbers come from, and every name it appears under.

Tracked since
May 10, 2026
Newest source mention
Aug 18, 2026

Where the results come from

Verification: 48 scores · 30 independently verified · 8 aggregator-attributed · 4 vendor cross-reference · 6 vendor-reported. How these tiers are assigned

From 14 sources on 6 sites. Hugging Face supplies 16 of them; the 30 independently verified results come from 4 sites. Bars are coloured by trust tier.

  • huggingface.co16
  • artificialanalysis.ai9
  • storage.googleapis.com7
  • api.llm-stats.com6
  • raw.githubusercontent.com6
  • x.ai4

Also known as

gpt-4 (0613)gpt-4 0314GPT-4 1106 (Inspect)gpt-4-0125-previewgpt-4-0613gpt-4-1106-previewgpt4GPT4 (Non-Reasoning)GPT4 (Reasoning)GPT40