o3 mini medium
LatestOpenAI
•
Proprietary# 29
Released
Jan 31, 2025
# 13
Knowledge Cutoff
Oct 23
# 6
Context Length
200K
Benchmarks
# 22
Code RankedAGI
59.9%
# 16
Aider Polyglot
53.8%
# 16
SWEBench Verified
42.9%
# 18
WebDev Arena
1100.18
# 10
LiveCodeBench v6
64.3%
# 2
LiveCodeBench v5
79.2%
# 5
Codeforces ELO
2036
# 20
Code LMArena
1309
# 12
Code LiveBench (old)
65.4%
# 14
GPQA Diamond
76.8%
# 4
Reason LiveBench (old)
86.3%
# 32
ELO LMArena
1305
# 20
AIME 2025 I & II
76.5%
# 2
MATH
97.3%
# 7
Humanity Last Exam
13.4%
# 5
NYT Connections
52.5%
# 18
MMLU
85.9%
# 17
AIME 2024
79.6%
# 4
IF LiveBench (old)
83.2%
# 8
Avg LiveBench (old)
70.0%
Pricing
# 23
Input Cost /M
$1.1
# 27
Output Cost /M
$4.4
# 12
Cached Cost /M
$0.55