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 3.6 Flash

AnthropicvsGoogle34 shared benchmarks1618 head-to-head
BenchmarkClaude Opus 4.6Gemini 3.6 Flash
AA Agentic Index67.640.5
AA Intelligence44.952
AA-LCR74.379
AA-Omniscience13.722.1
aime_202696.796.7
arc_agi_19334.5
ARC-AGI-268.82.6
arena_elo14971481
arena_text_factuality14871470
Artificial Analysis Coding Index48.169.2
charxiv_reasoning_with_tools84.789.4
charxiv_rq69.185.2
coding_arena_elo15451538
critpt12.610.6
gdpval55.946.1
GPQA Diamond91.392.8
HLE53.140.8
hmmt_feb_202696.289.4
livebench_agentic_coding4943.4
livebench_coding78.277.9
livebench_data_analysis69.963
livebench_instruction_following63.375.4
livebench_language83.383.9
livebench_math89.386.4
livebench_reasoning88.785.2
matharena_visual_math_overall72.387.8
MMMU-Pro77.383.2
mrcr_v2_8needle_128k_average8491.8
OmniScience Accuracy4750
OmniScience Non-Hallucination37.244.4
OSWorld-Verified72.783
scicode5252.7
simpleqa_verified46.568.7
SWE-bench Pro57.358.7

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.