GPT-4 Turbo

OpenAI · openai/gpt-4-turbo

ProviderOpenAI
Familygpt
Typevlm
Statusactive
Released2023-11-06
Updated2024-04-09

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)unassessed89.4
AlpacaEvalunassessed55.0
Arena Elo — Codingunassessed1270.0
Arena Elo — Hard Promptsunassessed1315.4
Arena Elo — Mathunassessed1250.0
Arena Elo — Overall (Text)unassessed1260.0
Arena Elo — Style Controlunassessed1323.4
Arena Elo — Visionunassessed1112.5
Artificial Analysis Intelligence Indexunassessed79.0
Artificial Analysis Output Speedunassessed65.0
BBQ (Bias Benchmark for QA)unassessed85.5
ChartQAunassessed87.2
DocVQAunassessed87.2
FLORES English-to-Germanunassessed67.3
FLORES English-to-Spanishunassessed71.2
FLORES English-to-Japaneseunassessed61.4
FLORES English-to-Chineseunassessed59.7
GPQA Diamondunassessed49.3
GSM8Kunassessed93.0
HELM Safetyunassessed89.5
HumanEvalunassessed87.8
IFEvalunassessed82.0
LiveCodeBenchunassessed29.1
MATH-500unassessed72.2
MathVistaunassessed50.5
MGSM (Multilingual Grade School Math)unassessed88.5
MMLU-Prounassessed67.4
MMMUunassessed59.4
MultiPL-E: C#unassessed80.5
MultiPL-E: Juliaunassessed61.8
MultiPL-E: Kotlin (unconfirmed)unassessed73.8
MultiPL-E: Luaunassessed56.8
MultiPL-E: Perlunassessed52.5
MultiPL-E: PHPunassessed78.2
MultiPL-E: Runassessed58.2
MultiPL-E: Rubyunassessed68.5
MultiPL-E: Scalaunassessed62.8
MultiPL-E: Swiftunassessed66.5
ToxiGenunassessed93.2

Data

This card as JSON · Edit on GitHub