o3 mini high
LatestOpenAI
•
Proprietary# 88
Released
Jan 31, 2025
# 19
Knowledge Cutoff
Oct 23
# 9
Context Length
200K
Benchmarks
# 90
Code RankedAGI
51.2%
# 50
SWEBench Verified
49.3%
# 103
Agentic RankedAGI
42.2%
# 24
LiveCodeBench v6
68.9%
# 1
LiveCodeBench v5
80.5%
# 15
Code LMArena
1332
# 10
Codeforces ELO
2130
# 18
Aider Polyglot
60.4%
# 2
Code LiveBench (old)
82.7%
# 82
Reason RankedAGI
52.4%
# 55
HLE
14.0%
# 50
GPQA Diamond
79.7%
# 53
Text Arena
1363
# 26
AIME 2025 I & II
86.5%
# 12
AIME 2024
87.3%
# 10
NYT Connections
61.4%
# 19
MMLU
86.9%
# 2
Halluc. Hughes
0.8%
# 2
Avg LiveBench (old)
75.8%
# 11
Coding LiveBench 25.4
65.5%
# 3
Data LiveBench
70.6%
# 13
Language LiveBench
50.7%
# 61
Math RankedAGI
68.8%
# 88
RAGI RankedAGI
50.5%
# 56
GDPval AA
748
Pricing
# 31
Input Cost /M
$1.1
# 36
Output Cost /M
$4.4
# 28
Cached Cost /M
$0.55