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 4 Opus vs Claude Opus 4.8

AnthropicvsAnthropic18 shared benchmarks117 head-to-head
BenchmarkClaude 4 OpusClaude Opus 4.8
AA Intelligence31.757.3
AA-LCR4073
arc_agi_12792.5
ARC-AGI-28.672.1
arena_vision12071280
Artificial Analysis Coding Index3474.3
Fortress27.618.2
frontiermath_tier_44.231.3
GPQA Diamond79.693.6
HLE12.357.9
IFBench53.762.2
livebench74.677.2
longbench_v255.669.1
scicode40.953.5
simplebench58.864.8
SWE-bench Verified79.488.6
Terminal-Bench Hard31.158.3
τ²-Bench Telecom (AA run)73.494.4

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.