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 Opus 4.8 vs DeepSeek-V3

AnthropicvsDeepSeek22 shared benchmarks220 head-to-head
BenchmarkClaude Opus 4.8DeepSeek-V3
AA Agentic Index49.41.6
AA Intelligence57.315.4
AA-LCR7341.3
AA-Omniscience28.8-37.6
Artificial Analysis Coding Index74.323
critpt20.90
gdpval54.20
GPQA Diamond93.668.4
HLE57.95.2
IFBench62.241
livebench77.272.4
longbench_v269.148.7
OmniScience Accuracy48.825.4
OmniScience Non-Hallucination60.723.3
scicode53.535.8
simplebench64.827.2
SWE-bench Verified88.642
TauBench V3 - Banking34.24.7
Terminal-Bench 2.18516.9
Terminal-Bench Hard58.315.2
τ²-Bench Telecom (AA run)94.447.1
τ³-Bench27.64.7

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.