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 Opus 4.5

AnthropicvsAnthropic25 shared benchmarks124 head-to-head
BenchmarkClaude 3.5 SonnetClaude Opus 4.5
AA Intelligence1041.9
AIME 20257.492.8
Artificial Analysis Coding Index30.247.8
C-Eval76.792.2
Fortress1313.6
frontiermath_tier_404.2
GPQA Diamond67.287
HLE3.930.8
hmmt_feb_20251.792.9
LiveCodeBench32.887
LiveCodeBench v637.284.8
longbench_v24164.4
MathVista67.780.2
mmlu_redux88.995.6
MMLU-Pro7890
MMMU7280.7
MMMU-Pro54.774
MMStar62.273.2
OCRBench79086.5
RealWorldQA60.177
scicode36.650
SEAL VISTA38.746.4
simplebench41.462
supergpqa48.270.6
SWE-bench Verified50.881.5

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.