Claude 3.5 Sonnet
OldAnthropic
•
Proprietary# 61
Released
Jun 20, 2024
# 9
Knowledge Cutoff
Apr 24
# 6
Context Length
200K
Benchmarks
# 48
Code RankedAGI
44.0%
# 18
SWEBench Verified
33.4%
# 30
LiveCodeBench v5
36.0%
# 23
Code LMArena
1282
# 18
Code LiveBench 24.11
60.9%
# 32
GPQA Diamond
59.4%
# 20
Reason LiveBench
58.7%
# 33
ELO LMArena
1268
# 25
Math LiveBench
53.3%
# 28
MATH
71.1%
# 5
Human Eval
92.0%
# 12
Human Eval+
81.7%
# 14
MMLU Pro
76.1%
# 7
MMLU
88.7%
# 17
MMMU
68.3%
# 8
Aidan Bench
1439
# 35
IF LiveBench
68.0%
# 25
Data LiveBench
56.7%
# 10
Lang LiveBench
53.2%
# 22
Avg LiveBench
59.7%
Pricing
# 27
Input Cost /M
$3
# 33
Output Cost /M
$15