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 GPT-5.6 Sol

AnthropicvsOpenAI44 shared benchmarks935 head-to-head
BenchmarkClaude Opus 4.6GPT-5.6 Sol
AA Agentic Index67.657.8
AA Intelligence44.961
AA-LCR74.377.7
AA-Omniscience13.722
aime_202696.799.9
arc_agi_19397.5
arc_agi_30.57.8
ARC-AGI-268.892.5
arena_elo14971482
arena_text_factuality14871474
Artificial Analysis Coding Index48.178.3
baby_vision_with_python38.488.9
browsecomp86.890.4
charxiv_rq69.187.8
coding_arena_elo15451619
critpt12.632.3
cybergym73.883.6
gdpval55.961.1
GPQA Diamond91.394.6
HiL-Bench38.332.3
HLE53.149.5
HLE (with tools)62.758
IFBench62.572.7
livebench_agentic_coding4956.2
livebench_coding78.283.9
livebench_data_analysis69.979.8
livebench_instruction_following63.371.8
livebench_language83.387.7
livebench_math89.396.2
livebench_reasoning88.791.7
mathvision71.295.8
MCP Atlas76.883.6
MMMU-Pro77.384.6
officeqa_pro57.163.2
OmniScience Accuracy4759.4
OmniScience Non-Hallucination37.210.6
OSWorld-Verified72.783
scicode5256.9
simplebench67.664.8
simpleqa_verified46.571.6
SWE-bench Pro57.364.6
Terminal-Bench Hard65.465.9
toolathlon56.858
τ²-Bench Telecom (AA run)99.385.1

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.