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 Gemini 2.5 Pro

AnthropicvsGoogle28 shared benchmarks523 head-to-head
BenchmarkClaude 3.5 SonnetGemini 2.5 Pro
AA Intelligence1027
aider_polyglot45.382.2
AIME 20257.488.3
AIR-Bench 202485.973.6
anthropic_red_team99.899.5
arena_vision11461246
Artificial Analysis Coding Index30.246.7
bbq94.996.4
Fortress1354.9
frontiermath_tier_404.2
GPQA Diamond67.284.4
harmbench98.165.4
HLE3.922.5
hmmt_feb_20251.782.5
LiveCodeBench32.882.7
MathVista67.783.9
MMLU-Pro7886
MMMU7283.9
MMMU-Pro54.774.9
MMStar62.279.2
OCRBench79085.9
scicode36.643
SEAL VISTA38.750.8
simple_safety_tests10097
simplebench41.462.4
simpleqa28.450.8
SWE-bench Verified50.867.2
xstest95.698.7

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.