Inference
Explore
Leaderboard
Benchmarks
Labs
Run locally
Search
⌘K
EN
English
Русский
Локально
中文
本地运行
12 Nov
2026
Benchmarks
/
MMMLU
MMMLU
In index
Knowledge
Best in knowledge
Models
?
Models with a result.
15
Top result
?
Best result on this benchmark.
90.9
%
Interfaze Beta
Top-3 spread
?
Points from first to third.
1.9
pts
Year
?
Year of release.
—
Result and price
0
20
40
60
80
100
$0.1
$0.3
$1
$3
$10
RESULT
PARETO
OUTPUT PRICE PER 1M TOKENS · LOG SCALE
5 of 15 results
Download
PNG
Results
15 results
Export
CSV
Export
JSON
#
Model
Result
?
The score from the source.
01
IN
Interfaze Beta
90.9
%
02
Qwen3.7 Max
90.3
%
03
Qwen3.7 Plus
89.0
%
04
Claude 4 Opus Thinking
88.8
%
05
Claude 4 Opus
87.4
%
06
LA
K-EXAONE 2.0
86.6
%
07
Claude 3.7 Sonnet Thinking
86.1
%
08
Qwen3 235B-A22B (Reasoning)
84.3
%
09
Gemma 4 12B
83.4
%
10
Claude 3.7 Sonnet
83.2
%
11
QwQ-32B
80.9
%
12
Qwen3 32B (Reasoning)
80.6
%
13
Qwen3 235B-A22B
79.8
%
14
Qwen3 32B
76.5
%
15
Phi-3.5-mini
55.4
%