Skip to content
Leaders Board.
Models/OpenAIOpen weights

gpt-oss-120b

Ranked on the boards below.
-
Overall rank
-
Podium score
0
Board wins
Aug 5, 2025
Released
·Chat·Reasoning·Coding

Chat

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

25
MultiChallenge
45.3% · of 29
as “gpt-oss-120b”

Reasoning

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

58
MMLU-Pro
80.8% · of 100 · stale since 2026-03-11
as “GPT-oss-120B(high)”
84
GPQA Diamond
75.8% · of 100
as “openai/gpt-oss-120b_high”
95
AA Intelligence
11.6 · of 100
as “gpt-oss-120b (high)”

Coding

Fixing real repositories, building web apps, editing code.

30
Aider Polyglot
41.8% · of 50 · stale since 2025-10-03
as “gpt-oss-120b (high)”
33
SWE-bench Verified
26.0% · of 39 · stale since 2026-02-26
as “gpt-oss-120b”

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.