Technology ❯ Artificial Intelligence ❯ Benchmarking

Performance Metrics

Intelligence Index Comparative Analysis GPT-5.2 Performance GPU Performance Claude Sonnet 4.6 APEX-Agents MMLU and HumanEval Scores Qwen3.5 35B A3B Image Generation Models User Testing LM Arena IndicVoices SWE-Bench LMArena Leaderboard GLM-5.2 vs Fable 5 Coding and Agent Tasks OmniBench Tau2-Bench Coding Benchmarks Model Comparison ARC-AGI Real-World Applications Model Evaluation Model Comparisons

9 ARTICLES

last wk.

Zhipu’s GLM‑5.2 Climbs Coding Rankings and Propels Stock Past HK$1 Trillion

A one‑million‑token context plus publicly released weights let developers run, inspect, adapt, host a frontier‑class coding AI, raising fresh questions about cost, efficiency, regulation

4 ARTICLES

2mo ago

Alibaba Launches Qwen 3.6 Max-Preview, Its Most Powerful AI Model

27 ARTICLES

4mo ago

Google Releases Gemini 3.1 Pro in Preview With Major Reasoning Gains