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 Sonnet 4.6 vs Muse Spark 1.1

AnthropicvsMeta32 shared benchmarks824 head-to-head
BenchmarkClaude Sonnet 4.6Muse Spark 1.1
AA Agentic Index61.639.7
AA Intelligence48.453.2
AA-LCR7481.3
AA-Omniscience12.228.1
arena_elo14721491
arena_text_factuality14601466
Artificial Analysis Coding Index6371.3
charxiv_reasoning_with_tools85.388.4
coding_arena_elo15231539
critpt3.115.1
DeepSWE 1.13053.3
Finance Agent v25157.2
gdpval54.843.7
GPQA Diamond89.989.8
healthbench_professional44.259.3
HLE4962.1
livebench_agentic_coding42.658.5
livebench_coding79.377.2
livebench_data_analysis7872.5
livebench_instruction_following63.269.6
livebench_language76.174.3
livebench_math8787.1
livebench_reasoning84.887.7
MCP Atlas69.588.1
OmniScience Accuracy40.952
OmniScience Non-Hallucination51.650
OSWorld-Verified78.580.8
scicode4758.2
SWE-bench Pro58.161.5
TauBench V3 - Banking34.431.8
Terminal-Bench 2.171.280
toolathlon49.475.6

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.