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

DeepSeek-V4-Flash vs Qwen3.7 Plus Preview

DeepSeekvsAlibaba31 shared benchmarks1912 head-to-head
BenchmarkDeepSeek-V4-FlashQwen3.7 Plus Preview
AA Agentic Index61.320.8
AA Intelligence51.839.4
AA-LCR74.369
AA-Omniscience-14.32.4
Agents' Last Exam25.233.6
Apex (Pass@1)3322.7
arena_elo14391458
arena_text_factuality14341454
Artificial Analysis Coding Index69.155.9
critpt16.69.1
gdpval52.922.2
GPQA Diamond90.890.3
HLE38.635.6
hmmt_feb_202694.892.9
IFBench79.279.1
imo_answer_bench88.486
MCP Atlas6973.2
MMLU-Pro86.488.5
nl2repo54.241.1
OmniScience Accuracy40.422.5
OmniScience Non-Hallucination15.674.5
scicode49.951.3
SWE-bench Multilingual73.375.8
SWE-bench Pro52.657.6
SWE-bench Verified7977.7
TauBench V3 - Banking39.417.9
Terminal-Bench 2.056.970.3
Terminal-Bench 2.182.761
Terminal-Bench Hard38.647
τ²-Bench Telecom (AA run)95.693
τ³-Bench22.917.9

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.