Skip to content
Leaders Board.
Models/OpenAIClosed

GPT 4o

Ranked on the boards below.
-
Overall rank
-
Podium score
0
Board wins
Nov 20, 2024
Released
·Chat·Reasoning·Coding·Agents and tools·Vision

Chat

Which model people prefer in blind head-to-head conversations.

65
Text Arena
1,443 · of 100
as “chatgpt-4o-latest-20250326”

Reasoning

Hard questions with checkable answers: science, math, puzzles, expert exams.

42
HLE
2.7% · of 42
as “GPT-4o (November 2024)”
70
ARC-AGI-2
0.0% · of 78
as “GPT-4o”
72
MMLU-Pro
77.9% · of 100 · stale since 2026-03-11
as “GPT-4o (2024-11-20)”

Coding

Fixing real repositories, building web apps, editing code.

28
Aider Polyglot
45.3% · of 50 · stale since 2025-10-03
as “chatgpt-4o-latest (2025-03-29)”
35
SWE-bench Verified
21.6% · of 39 · stale since 2026-02-26
as “GPT 4o (2024-11-20)”

Agents and tools

Calling functions and tools, using MCP servers, searching the web.

33
Search Arena
1,006 · of 33
as “api-gpt-4o-search”

Vision

Understanding images, charts and documents.

45
Vision Arena
1,240 · of 100
as “chatgpt-4o-latest-20250326”

More from OpenAI

GPT-6 SolGPT-6 AstraGPT-5.6 SolGPT-5.6 TerraGPT-5.5 Pre ReleaseGPT-5.5 Pro Pre ReleaseGPT-5.5 ProGPT-5.5

Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.

Weekly: the AI leaderboards with a new #1, Saturday mornings.