Inference
EN
OpenAI

GPT-3.5 Turbo

GPT-3.5 Turbo is a model from OpenAI. It has 5 scored results in 3 categories. It has no index.

  • Input: text
  • Released 2023-05
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.40%
SpeedOutput tokens per second.121/sMedian 67/s
First tokenSeconds to the first output token.0.5 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.50batch $0.25Median $0.60
Output / 1MUS dollars per 1M output tokens.$1.50batch $0.75 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.16KMedian 262K
EloLMArena rating and rank.1125±5 #359Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-3.5-turbo
Max outputMaximum output tokens per request.
4K
Knowledge cutoffLast date of training data.
30 Sep 2021
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.1 counted41.0—
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.1 counted5.0—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.3 counted15.6—

Results

5 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH level 5Math13.8% ±0.678 / 88
OTIS Mock AIME 2024-2025Math2.2% ±2.2183 / 200
GPQA diamond · Epoch AIKnowledge27.6% ±2.0201 / 217
Mystery Game PuzzlesReasoning3.0% ±1.779 / 80
GPQA Diamond · Vals AIKnowledge30.6% ±2.3134 / 135
FrontierMath-Tiers-1-3-v2-PrivateMath0.0%90 / 90
LegalBenchLegal64.4% ±0.6136 / 149
MedQAHealthcare58.5% ±0.987 / 95

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedEpoch AICC BY

History

5 releases
Output / 1M$1.50 → $1.50
23 Oct 202612 Nov 2026

Questions

How much does GPT-3.5 Turbo cost?
$0.50 per 1M input tokens, $1.50 per 1M output tokens.
How fast is GPT-3.5 Turbo?
121 output tokens per second, 0.5 s to the first token.
What is the context window of GPT-3.5 Turbo?
16K tokens.
When was GPT-3.5 Turbo released?
May 2023.

More from OpenAI

All models
GPT-4UnrankedGPT-3.5 Turbo 16kUnrankedGPT-3.5 Turbo InstructUnrankedGPT-4 TurboUnrankedGPT-3.5 Turbo (older v0613)Unranked