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 Qwen3.7 Max

AnthropicvsAlibaba39 shared benchmarks1722 head-to-head
BenchmarkClaude Sonnet 4.6Qwen3.7 Max
AA Agentic Index61.630.9
AA Intelligence48.446.7
AA-LCR7474.7
AA-Omniscience12.213.5
arena_elo14721474
arena_text_factuality14601479
Artificial Analysis Coding Index6366
coding_arena_elo15231517
critpt3.113.4
DeepSWE 1.13021.6
Finance Agent v25148.4
gdpval54.838.5
GPQA Diamond89.992.4
HLE4941.4
HLE (with tools)46.853.5
IFBench56.680.5
itbenchSre39.842.5
livebench75.574.3
livebench_agentic_coding42.643.6
livebench_coding79.374.2
livebench_data_analysis7871.8
livebench_instruction_following63.274
livebench_language76.179.7
livebench_math8785.3
livebench_reasoning84.883.3
MCP Atlas69.576.4
mmmlu89.390.3
OmniScience Accuracy40.931.1
OmniScience Non-Hallucination51.674.4
scicode4753.5
simpleqa_verified2958.5
SWE-bench Pro58.160.6
SWE-bench Verified79.680.4
TauBench V3 - Banking34.411.8
Terminal-Bench 2.059.169.7
Terminal-Bench 2.171.275
Terminal-Bench Hard59.150.8
τ²-Bench Telecom (AA run)97.994.7
τ³-Bench30.510.9

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.