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 4.5 vs Gemini 3.5 Flash

AnthropicvsGoogle41 shared benchmarks932 head-to-head
BenchmarkClaude Opus 4.5Gemini 3.5 Flash
AA Agentic Index59.670.4
AA Intelligence41.952
AA-LCR7681
AA-Omniscience1421.2
aime_202695.195
arc_agi_18292.5
ARC-AGI-237.672.1
arena_elo14731477
arena_text_factuality14581466
Artificial Analysis Coding Index47.870.1
charxiv_rq68.584.2
coding_arena_elo14951490
critpt4.613.1
finance_agent55.257.9
frontiermath_tier_44.214.6
gdpval47.357.8
GPQA Diamond8792.2
HLE30.842.7
hmmt_feb_202685.395.5
IFBench5876.3
livebench7675
livebench_agentic_coding39.749
livebench_coding79.778.2
livebench_data_analysis74.464.9
livebench_instruction_following62.575.6
livebench_language81.384.6
livebench_math90.488.2
livebench_reasoning80.182
MCP Atlas69.883.6
MMMU-Pro7484.3
OmniScience Accuracy46.651.4
OmniScience Non-Hallucination3938.2
OSWorld-Verified66.378.4
scicode5053.1
simplebench6276.7
simpleqa_verified41.868.4
SWE-bench Pro57.155.1
Terminal-Bench 2.059.376.2
Terminal-Bench Hard4746.2
toolathlon43.556.5
τ²-Bench Telecom (AA run)89.595.6

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.