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 Opus 4.6

AnthropicvsAnthropic31 shared benchmarks427 head-to-head
BenchmarkClaude 3.7 SonnetClaude Opus 4.6
AA Agentic Index3767.6
AA Intelligence27.644.9
AA-LCR62.374.3
AA-Omniscience-0.713.7
AIME 202554.899.8
arc_agi_113.693
ARC-AGI-2068.8
arena_vision11951300
Artificial Analysis Coding Index36.448.1
critpt0.912.6
Fortress3820.5
gdpval27.455.9
GPQA Diamond84.891.3
HLE9.753.1
IFBench48.362.5
metr_hcast54.277
metr_re_bench097.4
metr_swaa98.798.5
mmmlu86.191.1
MMMU-Pro60.177.3
multichallenge51.656
MultiNRC27.857.1
OmniScience Accuracy28.247
OmniScience Non-Hallucination6037.2
scicode40.352
SEAL VISTA48.246.1
simplebench46.467.6
swe_bench_bash52.875.6
SWE-bench Verified70.380.8
Terminal-Bench Hard21.265.4
τ²-Bench Telecom (AA run)54.799.3

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.