OpenAI

GPT-3.5 Turbo

GPT-3.5 Turbo is a proprietary model from OpenAI, released Jan 25, 2024. It ranks #356 of 351 on the LMArena text leaderboard with a rating of 1125. It costs $1 per million input tokens and $2 per million output tokens, with a 4K-token context window.

LMArena text1125+0 in 30 days
Rank#356/351
95% interval1120–1130
Votes66.2K
Developer
OpenAI
Released
Jan 25, 2024
Context window
4K
Price in / out, per 1M tokens
$1 / $2
Weights
Proprietary
Inputs
Text
Reasoning
No
Tool use
Yes
GPT-3.5 Turbo, LMArena text rating over time
9901030107011101150Dec 23Aug 24May 25Feb 26Oct 26
LatestGPT-3.5 Turbo 1125

The rating LMArena published at each update since Dec 6, 2023. Ratings move as votes come in and new models join.

Benchmarks

BenchmarkScore barAccuracyRankCost / test
MedQAMedicine58.47%84 / 92$0.5 / $1.5
GPQA DiamondReasoning30.56%137 / 138$0.5 / $1.5

Vals AI, as of Oct 24, 2026.

LMArena, by category

LeaderboardRatingRankVotes
TextLMArena1125356 / 35166.2K
CodingLMArena1136347 / 34611.1K
MathLMArena1142342 / 3398.6K
Creative writingLMArena1092364 / 3499.7K
Instruction followingLMArena1119345 / 35123.5K
Hard promptsLMArena1108355 / 35118.5K
Multi-turnLMArena1117347 / 34910.3K
Long queriesLMArena1121349 / 3306.7K
ExpertLMArena1070341 / 305437
Legal and governmentIndustries1118346 / 3253.6K
Medicine and healthcareIndustries1074347 / 3253.8K
Business and financeIndustries1076360 / 3446.9K
ChineseLanguages1075351 / 3287.6K
SpanishLanguages1121283 / 249895
GermanLanguages1091286 / 2611.9K
FrenchLanguages1118280 / 2521.3K
JapaneseLanguages1043258 / 236965

LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (GPT-3.5 Turbo (0125), GPT-3.5 Turbo (1106)).

Compare GPT-3.5 Turbo

OpenAI

The lab behind GPT and ChatGPT, which brought large language models to hundreds of millions of people. Founded 2015, based in San Francisco. openai.com

Questions

Who makes GPT-3.5 Turbo?

GPT-3.5 Turbo is made by OpenAI, founded 2015 and based in San Francisco.

How much does GPT-3.5 Turbo cost?

$1 per million input tokens and $2 per million output tokens, at its provider’s list price.

What is GPT-3.5 Turbo’s context window?

4K tokens (4,095).

How does GPT-3.5 Turbo rank?

#356 of 351 on LMArena’s text leaderboard, rated 1125 (95% interval 1120–1130) from 66,207 votes, as of Oct 22, 2026.

Is GPT-3.5 Turbo open source?

No. GPT-3.5 Turbo is proprietary and served through its provider’s API.

Sources

Every number on this page comes from these sources; models without a published number show none. Download the data. Cite as “Nexus Explorer, nexus.inc/models”.