GLM 4.6V
Open Sourcedi z-ai · Rilascio 2025-12-08
40.1
punteggio medio
$0.30/1M
Prezzo Input
$0.90/1M
Prezzo Output
131K tokens (~66 books)
Finestra di Contesto
multimodal
Tipo
Tested on 9 benchmarks with 40.1% average. Top scores: Chatbot Arena Elo — Overall (1377.9%), LiveBench — Coding (64.2%), LiveBench — Mathematics (62.5%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1377.9 | |
| LiveBench — Coding | coding | 64.2 | |
| LiveBench — Mathematics | math | 62.5 | |
| LiveBench — Language | language | 49.7 | |
| LiveBench — Data Analysis | reasoning | 46.4 | |
| LiveBench — Overall | knowledge | 40.1 | |
| LiveBench — Reasoning | reasoning | 37.2 | |
| LiveBench — If | language | 17.1 | |
| LiveBench — Agentic Coding | coding | 3.3 |