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 Opus 5

Z.aivsAnthropic35 shared benchmarks134 head-to-head
BenchmarkGLM-5.2 Full Open SourceOpus 5
AA Agentic Index45.759.2
AA Intelligence52.663.1
AA-LCR76.778.7
AA-Omniscience4.437.1
arc_agi_17797.5
ARC-AGI-222.890.4
arena_elo14711487
arena_text_factuality14601481
Artificial Analysis Coding Index68.878
coding_arena_elo15821662
critpt20.929.1
DeepSWE 1.14468.8
gdpval50.367.2
GDPval-AA v215141861
GPQA Diamond91.293.7
HiL-Bench43.757
HLE54.764.7
HLE (with tools)54.764.7
livebench_agentic_coding51.865.2
livebench_coding79.781.5
livebench_data_analysis73.774.5
livebench_instruction_following62.363.8
livebench_language76.288.7
livebench_math89.895.7
livebench_reasoning78.691.2
MCP Atlas82.685.8
officeqa_pro41.466.9
OmniScience Accuracy24.360.9
OmniScience Non-Hallucination73.740.5
scicode50.555.7
simplebench58.880.6
simpleqa_verified38.156.7
SWE-bench Pro62.179.2
TauBench V3 - Banking34.644.7
Terminal-Bench 2.182.789.1

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.