M
MODELYST
AI research terminal
●
live · verified Jul 13
Search
⌘K
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Leaderboards
/
MMLU Leaderboard
LDR
MMLU Leaderboard
MMLU
☆ Watch
Models ranked by MMLU accuracy.
1
o1
Dec 1, 2024
91.8
2
Claude 3.5 Sonnet
Oct 1, 2024
88.7
3
GPT-4o
Aug 1, 2024
88.7
4
DeepSeek-V3
May 31, 2026
88.5
5
Grok-2
Aug 1, 2024
87.5
6
Claude 3 Opus
Mar 1, 2024
86.8
7
Qwen2.5-72B-Instruct
May 31, 2026
86.1
8
Llama-3.1-70B-Instruct
May 31, 2026
86
9
Llama-3.3-70B-Instruct
May 31, 2026
86
10
Gemini 1.5 Pro
Sep 1, 2024
85.9
11
GPT-4o mini
Jul 1, 2024
82
12
gemma-2-27b-it
May 31, 2026
75.2
13
Qwen2.5-7B-Instruct
May 31, 2026
74.2
14
gemma-2-9b-it
May 31, 2026
71.3
15
Llama-3.1-8B-Instruct
May 31, 2026
69.4
16
Phi-3.5-mini-instruct
May 31, 2026
69
17
Mistral-7B-Instruct-v0.3
May 31, 2026
62.5