0

GPT-4o

GPT-4o is an AI model from OpenAI.

Publisher
OpenAI
Family
GPT
Context
128K
Input
Output
License
proprietary
Released
20 Nov 2024

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →
Context
128K
Weights
Closed
API only
Input
$2.50
/1M tok
Output
$10
/1M tok
Blended
$4.38
#455/ 499/1M · 3:1
Speed
0
#103/ 498tok/s
Cache read
$1.25
0.50x input

Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter

Reported on 33 evals across 10 domains - best 75.9% on MATH-500 · #106 of 190

Reported eval scores

33
Taubench61.2
Medqa Followup10.8
GSM8K96.1
Chem Qa0.3
Traveling Salesman1
ScholarSearch5.7
AIME202438
TaxEval v274.5
MortgageTax57.4
CorpFin v245.9
LiveBench - Instruction Following70.1
LiveBench - Language49
Terminal-Bench (Hard)8.3
LiveBench - Coding46.1
IFBench34.3
MMLU-Pro74.8
LiveBench55.1
Humanity's Last Exam (HLE)2.4
τ-bench (tau-bench)32.5
τ²-bench (Tau²-bench)25.1

Head-to-heads

29

benchmark comparisons against other models

vs Gemini 2.5 Pro22 shared evalsvs Claude Sonnet 4.521 shared evalsvs GPT-4o-mini21 shared evalsvs GPT-4.1 Mini20 shared evalsvs GPT-5 Mini20 shared evalsvs Claude 4 Sonnet20 shared evalsvs GPT-519 shared evalsvs GPT-4.119 shared evalsvs GPT-5 Nano18 shared evalsvs GPT-5.218 shared evalsvs Claude Opus 4.518 shared evalsvs DeepSeek V3.218 shared evalsvs gpt-oss-120b17 shared evalsvs GPT-4.1 Nano16 shared evalsvs Grok 4.1 Fast16 shared evalsvs GLM 4.716 shared evalsvs GPT-5.515 shared evalsvs Claude Opus 4.615 shared evalsvs Kimi K2.515 shared evalsvs Gemini 3.1 Pro Preview14 shared evalsvs Claude Opus 4.814 shared evalsvs GPT-5.414 shared evalsvs Claude Opus 4.714 shared evalsvs GLM 5.114 shared evalsvs Claude Sonnet 4.614 shared evalsvs Qwen3.6 Plus14 shared evalsvs GPT-5.4 Mini14 shared evalsvs Claude Fable 513 shared evalsvs GPT-6 Astra4 shared evals