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 3.7 Sonnet vs Claude Sonnet 4.6

AnthropicvsAnthropic22 shared benchmarks220 head-to-head
BenchmarkClaude 3.7 SonnetClaude Sonnet 4.6
AA Agentic Index3761.6
AA Intelligence27.648.4
AA-LCR62.374
AA-Omniscience-0.712.2
arc_agi_113.686.5
ARC-AGI-2060.4
arena_vision11951278
Artificial Analysis Coding Index36.463
critpt0.93.1
gdpval27.454.8
GPQA Diamond84.889.9
harmbench84.324.2
HLE9.749
IFBench48.356.6
mmmlu86.189.3
MMMU-Pro60.175.6
OmniScience Accuracy28.240.9
OmniScience Non-Hallucination6051.6
scicode40.347
SWE-bench Verified70.379.6
Terminal-Bench Hard21.259.1
τ²-Bench Telecom (AA run)54.797.9

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.