GPT-3.5-turbo

OpenAI · openai/gpt-3-5-turbo

ProviderOpenAI
Familygpt
Typellm-chat
Statusactive
Released2023-03-01
Updated2023-11-06

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
AlpacaEvalunassessed25.4
Arena Elo — Codingunassessed1100.0
Arena Elo — Mathunassessed1080.0
Arena Elo — Overall (Text)unassessed1110.0
Artificial Analysis Intelligence Indexunassessed60.0
Artificial Analysis Output Speedunassessed92.0
GPQA Diamondunassessed28.3
GSM8Kunassessed80.0
HumanEvalunassessed48.1
IFEvalunassessed60.5
MATH-500unassessed32.8
MGSM (Multilingual Grade School Math)unassessed56.3
MMLU-Prounassessed40.2

Data

This card as JSON · Edit on GitHub