BenchLeader

ChatGPT-4o

Quality#119 of 366
54.7Index
Above the median
+4.8 on the median

As of 21 Nov 2026, ChatGPT-4o by OpenAI scores 54.7 on the BenchLeader Index (650 ranked configurations), with its best results in human preference (62) and weakest in multimodal (51). Released 27 Mar 2025.

Key facts (as of 21 Nov 2026)

  • ChatGPT-4o was released on 27 Mar 2025 (OpenAI).

In detail. ChatGPT-4o is an OpenAI proprietary model, released 27 Mar 2025. Its best configuration ranks #243 of 650 on the BenchLeader Index at 54.7 ±4.9, in the upper half. The ± is the point: 317 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (62) and lowest in multimodal (51). Last measured 19 Nov 2026.

Blended price
–
Output speed
–
First answer
–
Context
128k
via Artificial Analysis
Cost per task
–
Tokens per task
–
Released
27 Mar 2025
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index55
  2. Reasoning61
  3. Coding52
  4. Maths58
  5. Human preference62
  6. Multimodal51

Embed this rank

More badge styles
[![ChatGPT-4o on BenchLeader: #118 overall](https://www.benchleader.com/badge/chatgpt-4o.svg?style=compact)](https://www.benchleader.com/models/chatgpt-4o)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when OpenAI ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

Versions

OpenAI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
ChatGPT-4othis page27 Mar 202554.7#243
ChatGPT-4o 012929 Jan 2025––

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
Arena Hard Prompts1455#118Arena (LMArena)
GPQA Diamond (AA)not in index65.5%#356Artificial Analysis
Humanity's Last Exam (AA)not in index4.0%#584Artificial Analysis
Arena Expertnot in index1430#152Arena (LMArena)

Coding

Maths

Benchmarknot statedSourceTrend
Arena Maths1403#160Arena (LMArena)
AIME 2025 (AA)not in index25.7%#189Artificial Analysis

Knowledge

Benchmarknot statedSourceTrend
Arena Text Factualitynot in index1444#93Arena (LMArena)

Instruction following

Benchmarknot statedSourceTrend
Arena Instruction Followingnot in index1427#109Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1443#99Arena (LMArena)
EQ-Bench Creative Writing v3not in index1501#58EQ-Bench
EQ-Bench Longform Writingnot in index60.2#60EQ-Bench
Arena Creative Writingnot in index1421#91Arena (LMArena)
Arena Multi-turnnot in index1470#67Arena (LMArena)
Arena Longer Queriesnot in index1440#121Arena (LMArena)

Multimodal

Benchmarknot statedSourceTrend
Arena Vision1243#72Arena (LMArena)
VISTA38.0%#45Scale AI SEAL

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.2not in index9.0#435Artificial Analysis
AA Progress Index v1not in index181.3#519Artificial Analysis

More from OpenAI

New this month

See also

Embed or cite

Show where ChatGPT-4o ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![ChatGPT-4o on BenchLeader: #118 overall](https://www.benchleader.com/badge/chatgpt-4o.svg)](https://www.benchleader.com/models/chatgpt-4o)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 21). ChatGPT-4o on the BenchLeader Index (method v1.5) [Data set]. Retrieved November 21, 2026, from https://www.benchleader.com/models/chatgpt-4o

BibTeX:

@misc{benchleader_chatgpt_4o_20261121,
  author       = {{BenchLeader}},
  title        = {{ChatGPT-4o on the BenchLeader Index (method v1.5)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/chatgpt-4o}},
  note         = {Data as of 2026-11-21}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are ChatGPT-4o's benchmark scores?
As of 21 Nov 2026, ChatGPT-4o scores 54.7 ±4.9 on the BenchLeader Index, strongest in human preference (62) and weakest in multimodal (51). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does ChatGPT-4o rank?
ChatGPT-4o is #243 of 650 ranked configurations on 21 Nov 2026. 317 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 70.2.
When was ChatGPT-4o released?
OpenAI released ChatGPT-4o on 27 Mar 2025.

Data as of 21 Nov 2026. Compare with another model.

Cite as: BenchLeader, “ChatGPT-4o: benchmarks, pricing, speed and rank”, data as of 21 Nov 2026, https://www.benchleader.com/models/chatgpt-4o.