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 4.6 vs Gemini 2.5 Flash

AnthropicvsGoogle32 shared benchmarks293 head-to-head
BenchmarkClaude Opus 4.6Gemini 2.5 Flash
AA Agentic Index67.618.8
AA Intelligence44.917.7
AA-LCR74.365.7
AA-Omniscience13.7-29.8
AIME 202599.872
arc_agi_19333.3
ARC-AGI-268.82.5
arena_text_factuality14871437
arena_vision13001214
Artificial Analysis Coding Index48.122.2
critpt12.61.4
frontiermath_tier_422.94.2
gdpval55.911.9
GPQA Diamond91.382.8
HLE53.112.1
IFBench62.550.3
LiveCodeBench88.876.2
MMMU-Pro77.369.1
OmniScience Accuracy4726.1
OmniScience Non-Hallucination37.224.7
scicode5235.9
SEAL VISTA46.149.1
simplebench67.641.2
swe_bench_bash75.628.7
SWE-bench Verified80.860.4
Terminal-Bench Hard65.413.6
vectara_answer_rate99.899
vectara_avg_summary_length137.6101.5
vectara_factual_consistency87.892.2
vectara_hallucination_rate12.27.8
VisualToolBench27.54.7
τ²-Bench Telecom (AA run)99.331.6

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.