Inference
Explore
Leaderboard
Benchmarks
Labs
Run locally
Search
⌘K
EN
English
Русский
Локально
中文
本地运行
12 Nov
2026
Benchmarks
/
MMLU-Pro first-party comparison snapshot
MMLU-Pro first-party comparison snapshot
In index
Knowledge
Best in knowledge
Models
?
Models with a result.
6
Top result
?
Best result on this benchmark.
89.1
%
Claude Opus 4.6
Top-3 spread
?
Points from first to third.
3.3
pts
Year
?
Year of release.
—
Result and price
0
20
40
60
80
100
$0.3
$1
$3
$10
$30
RESULT
PARETO
OUTPUT PRICE PER 1M TOKENS · LOG SCALE
6 of 6 results
Download
PNG
Results
6 results
Export
CSV
Export
JSON
#
Model
Result
?
The score from the source.
01
Claude Opus 4.6
89.1
%
02
MA
Kimi K2.5
87.1
%
03
GLM-5
85.8
%
04
AA
Trinity-Large-Thinking
83.4
%
05
MiniMax M2.7
80.8
%
06
AA
Trinity-Large-Preview
75.2
%