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 Gemini 3 Flash Preview

AnthropicvsGoogle26 shared benchmarks224 head-to-head
BenchmarkClaude 3.7 SonnetGemini 3 Flash Preview
AA Agentic Index3749.7
AA Intelligence27.638.7
AA-LCR62.373
AA-Omniscience-0.710.1
AIME 202554.899.7
arc_agi_113.684.7
ARC-AGI-2033.6
arena_vision11951260
Artificial Analysis Coding Index36.442.6
critpt0.98.6
gdpval27.435.2
GPQA Diamond84.890.4
harmbench84.370
HLE9.743.5
hmmt_feb_202531.797.5
IFBench48.378
mmmlu86.191.8
MMMU-Pro60.181.2
OmniScience Accuracy28.253.4
OmniScience Non-Hallucination607.6
scicode40.350.6
simplebench46.461.1
swe_bench_bash52.875.8
SWE-bench Verified70.378
Terminal-Bench Hard21.238.6
τ²-Bench Telecom (AA run)54.780.4

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.