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 Muse Spark 1.1

AnthropicvsMeta31 shared benchmarks1912 head-to-head
BenchmarkClaude Opus 4.7Muse Spark 1.1
AA Agentic Index64.639.7
AA Intelligence5553.2
AA-LCR75.381.3
AA-Omniscience27.328.1
arena_elo14941491
arena_text_factuality14741466
Artificial Analysis Coding Index73.671.3
charxiv_reasoning_with_tools9188.4
coding_arena_elo15571539
critpt1215.1
cybergym73.859
Finance Agent v251.557.2
gdpval58.643.7
GPQA Diamond94.289.8
HLE54.762.1
livebench_agentic_coding50.758.5
livebench_coding82.177.2
livebench_data_analysis78.372.5
livebench_instruction_following66.769.6
livebench_language77.974.3
livebench_math92.887.1
livebench_reasoning87.287.7
MCP Atlas79.188.1
OmniScience Accuracy48.952
OmniScience Non-Hallucination57.750
OSWorld-Verified82.880.8
scicode54.558.2
SWE-bench Pro64.361.5
TauBench V3 - Banking34.631.8
Terminal-Bench 2.183.180
toolathlon59.375.6

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.