VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Claude 3.5 Sonnet vs o1

AnthropicvsOpenAI35 shared benchmarks827 head-to-head
BenchmarkClaude 3.5 Sonneto1
AA Intelligence1024
aider_polyglot45.361.7
AIME 20241679.2
AIME 20257.481.7
AIR-Bench 202485.980
anthropic_red_team99.898.3
arena_vision11461193
Artificial Analysis Coding Index30.239.7
bbq94.997.3
Codeforces7172061
Codeforces (Percentile)20.396.6
Codeforces (Rating)7172061
DROP (3-shot F1)88.390.2
Fortress1319.4
GPQA Diamond67.275.7
GSM8K96.997.1
harmbench98.196.3
HLE3.97.7
humaneval93.788.1
livecodebench_pass1cot36.363.4
MATH81.396.4
math_500_em78.396.4
MathVista67.771.8
mgsm91.690.8
mmlu88.391.8
MMMU7277.6
scicode36.635.8
SEAL VISTA38.745.3
simple_safety_tests10099
simplebench41.441.7
simpleqa28.447
SWE-bench Verified50.848.9
TAU-bench (airline)4650
TAU-bench (retail)69.270.8
xstest95.697

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.