o3 mini high
LatestOpenAI
•
Proprietary# 24
Released
Jan 31, 2025
# 12
Knowledge Cutoff
Oct 23
# 6
Context Length
200K
Benchmarks
# 8
Code RankedAGI
67.2%
# 7
Code LiveBench
65.5%
# 8
Aider Polyglot
60.4%
# 8
SWEBench Verified
49.3%
# 3
Codeforces ELO
2130
# 11
WebDev Arena
1147.27
# 1
LiveCodeBench v5
80.5%
# 10
Code LMArena
1332
# 2
Code LiveBench 24.11
82.7%
# 5
GPQA Diamond
79.7%
# 3
Reason LiveBench
89.6%
# 19
ELO LMArena
1332
# 7
AIME 2025 I & II
86.5%
# 5
Math LiveBench
76.5%
# 1
MATH
97.9%
# 3
NYT Connections
61.4%
# 13
MMLU
86.9%
# 2
Halluc. Hughes
0.8%
# 8
AIME 2024
87.3%
# 2
IF LiveBench
84.4%
# 3
Data LiveBench
70.6%
# 13
Lang LiveBench
50.7%
# 2
Avg LiveBench
75.8%
Pricing
# 22
Input Cost /M
$1
# 27
Output Cost /M
$4.4
# 12
Cached Cost /M
$0.55