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 3.6 Flash

AnthropicvsGoogle31 shared benchmarks724 head-to-head
BenchmarkClaude Opus 4.5Gemini 3.6 Flash
AA Agentic Index59.640.5
AA Intelligence41.952
AA-LCR7679
AA-Omniscience1422.1
aime_202695.196.7
arc_agi_18234.5
ARC-AGI-237.62.6
arena_elo14731481
arena_text_factuality14581470
Artificial Analysis Coding Index47.869.2
charxiv_rq68.585.2
coding_arena_elo14951538
critpt4.610.6
gdpval47.346.1
GPQA Diamond8792.8
HLE30.840.8
hmmt_feb_202685.389.4
livebench_agentic_coding39.743.4
livebench_coding79.777.9
livebench_data_analysis74.463
livebench_instruction_following62.575.4
livebench_language81.383.9
livebench_math90.486.4
livebench_reasoning80.185.2
MMMU-Pro7483.2
OmniScience Accuracy46.650
OmniScience Non-Hallucination3944.4
OSWorld-Verified66.383
scicode5052.7
simpleqa_verified41.868.7
SWE-bench Pro57.158.7

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.