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 Gemini 2.5 Flash

AnthropicvsGoogle23 shared benchmarks230 head-to-head
BenchmarkClaude Opus 4.8Gemini 2.5 Flash
AA Agentic Index49.418.8
AA Intelligence57.317.7
AA-LCR7365.7
AA-Omniscience28.8-29.8
arc_agi_192.533.3
ARC-AGI-272.12.5
arena_text_factuality14641437
arena_vision12801214
Artificial Analysis Coding Index74.322.2
critpt20.91.4
frontiermath_tier_431.34.2
gdpval54.211.9
GPQA Diamond93.682.8
HLE57.912.1
IFBench62.250.3
MMMU-Pro78.969.1
OmniScience Accuracy48.826.1
OmniScience Non-Hallucination60.724.7
scicode53.535.9
simplebench64.841.2
SWE-bench Verified88.660.4
Terminal-Bench Hard58.313.6
τ²-Bench Telecom (AA run)94.431.6

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.