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 4.7 vs Gemini 3.6 Flash

AnthropicvsGoogle35 shared benchmarks2510 head-to-head
BenchmarkClaude Opus 4.7Gemini 3.6 Flash
AA Agentic Index64.640.5
AA Intelligence5552
AA-LCR75.379
AA-Omniscience27.322.1
aime_202695.896.7
arc_agi_19234.5
ARC-AGI-275.82.6
arena_elo14941481
arena_text_factuality14741470
Artificial Analysis Coding Index73.669.2
charxiv_reasoning_with_tools9189.4
charxiv_rq82.185.2
coding_arena_elo15571538
critpt1210.6
gdpval58.646.1
GPQA Diamond94.292.8
HLE54.740.8
hmmt_feb_202693.989.4
livebench_agentic_coding50.743.4
livebench_coding82.177.9
livebench_data_analysis78.363
livebench_instruction_following66.775.4
livebench_language77.983.9
livebench_math92.886.4
livebench_reasoning87.285.2
MMMU-Pro78.883.2
mrcr_v2_8needle_128k_average59.391.8
OmniScience Accuracy48.950
OmniScience Non-Hallucination57.744.4
OSWorld-Verified82.883
scicode54.552.7
simpleqa_verified50.668.7
SWE-bench Pro64.358.7
TauBench V3 - Banking34.629.9
Terminal-Bench 2.183.178

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.