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 Claude 3.7 Sonnet

AnthropicvsAnthropic25 shared benchmarks420 head-to-head
BenchmarkClaude 3.5 SonnetClaude 3.7 Sonnet
AA Intelligence1027.6
aider_polyglot45.364.9
AIME 20257.454.8
AIR-Bench 202485.981.8
anthropic_red_team99.899.7
arena_vision11461195
Artificial Analysis Coding Index30.236.4
bbq94.992.1
Fortress1338
GPQA Diamond67.284.8
harmbench98.184.3
HLE3.99.7
hmmt_feb_20251.731.7
ifeval90.193.2
math_500_em78.396.2
MMMU7275
MMMU-Pro54.760.1
scicode36.640.3
SEAL VISTA38.748.2
simple_safety_tests100100
simplebench41.446.4
SWE-bench Verified50.870.3
TAU-bench (airline)4658.4
TAU-bench (retail)69.281.2
xstest95.696.4

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.