GPT-4o

OpenAI · openai/gpt-4o

ProviderOpenAI
Familygpt
Typevlm
Statusactive
Released2024-05-13
Updated2024-08-06

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
AI2D (AI2 Diagrams)unassessed94.2
Aider Polyglot Benchmarkunassessed58.2
AlpacaEvalunassessed48.5
Arena Elo — Codingunassessed1300.0
Arena Elo — Hard Promptsunassessed1456.0
Arena Elo — Mathunassessed1270.0
Arena Elo — Overall (Text)unassessed1290.0
Arena Elo — Style Controlunassessed1443.0
Arena Elo — Visionunassessed1310.0
Artificial Analysis Intelligence Indexunassessed82.0
Artificial Analysis Output Speedunassessed78.0
BBQ (Bias Benchmark for QA)unassessed85.8
ChartQAunassessed85.2
DocVQAunassessed92.8
FinBenchunassessed68.5
FLORES English-to-Germanunassessed67.3
FLORES English-to-Spanishunassessed71.2
FLORES English-to-Japaneseunassessed61.4
FLORES English-to-Chineseunassessed59.7
GPQA Diamondunassessed53.6
GSM8Kunassessed95.0
HELM Safetyunassessed89.2
HumanEvalunassessed90.2
IFEvalunassessed84.3
LegalBenchunassessed72.1
LiveCodeBenchunassessed31.7
MATH-500unassessed76.6
MathVistaunassessed63.8
MedQAunassessed78.5
MGSM (Multilingual Grade School Math)unassessed90.5
MMLU: Astronomyunassessed78.2
MMLU: Biology (subcategory)unassessed86.8
MMLU: Business Ethicsunassessed80.2
MMLU: Chemistry (subcategory)unassessed80.2
MMLU: Clinical Knowledgeunassessed85.5
MMLU: Computer Science (subcategory)unassessed87.5
MMLU: Jurisprudenceunassessed78.5
MMLU: Physics (unresolved key)unassessed83.5
MMLU-Prounassessed72.6
MMLU: Professional Accountingunassessed70.5
MMLU: Professional Lawunassessed76.8
MMMUunassessed69.1
MT-Benchunassessed9.1
MultiPL-Eunassessed83.0
MultiPL-E: C++unassessed82.5
MultiPL-E: C#unassessed82.1
MultiPL-E: Gounassessed79.1
MultiPL-E: Javaunassessed86.5
MultiPL-E: JavaScriptunassessed85.8
MultiPL-E: Juliaunassessed62.8
MultiPL-E: Kotlin (unconfirmed)unassessed75.8
MultiPL-E: Luaunassessed58.5
MultiPL-E: Perlunassessed55.2
MultiPL-E: PHPunassessed80.5
MultiPL-E: Pythonunassessed90.2
MultiPL-E: Runassessed60.5
MultiPL-E: Rubyunassessed70.2
MultiPL-E: Rustunassessed72.8
MultiPL-E: Scalaunassessed64.5
MultiPL-E: Swiftunassessed68.2
MultiPL-E: TypeScriptunassessed84.2
OCRBenchunassessed73.6
RealWorldQAunassessed75.4
SWE-bench Agentunassessed32.1
SWE-bench Verifiedunassessed38.4
τ-benchunassessed42.5
Terminal-Benchunassessed35.2
ToxiGenunassessed92.8
WildBenchunassessed75.8

Data

This card as JSON · Edit on GitHub