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

GLM-5.2 Full Open Source vs Qwen3.7 Max

Z.aivsAlibaba43 shared benchmarks2715 head-to-head
BenchmarkGLM-5.2 Full Open SourceQwen3.7 Max
AA Agentic Index45.730.9
AA Intelligence52.646.7
AA-LCR76.774.7
AA-Omniscience4.413.5
aime_202699.297
arena_elo14711474
arena_text_factuality14601479
Artificial Analysis Coding Index68.866
coding_arena_elo15821517
critpt20.913.4
DeepSWE46.218
DeepSWE 1.14421.6
gdpval50.338.5
GPQA Diamond91.292.4
HLE54.741.4
HLE (with tools)54.753.5
hmmt_feb_202692.597.1
hmmt_nov_202594.495
IFBench73.380.5
imo_answer_bench9190
itbenchSre42.742.5
JobBench43.431.3
livebench_agentic_coding51.843.6
livebench_coding79.774.2
livebench_data_analysis73.771.8
livebench_instruction_following62.374
livebench_language76.279.7
livebench_math89.885.3
livebench_reasoning78.683.3
MCP Atlas82.676.4
MLS Bench Lite40.431.7
nl2repo48.947.2
OmniScience Accuracy24.331.1
OmniScience Non-Hallucination73.774.4
scicode50.553.5
simplebench58.870.4
simpleqa_verified38.158.5
SWE-bench Pro62.160.6
TauBench V3 - Banking34.611.8
Terminal-Bench 2.182.775
Terminal-Bench Hard50.850.8
τ²-Bench Telecom (AA run)99.194.7
τ³-Bench26.810.9

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.