GPT-5 Chat
di OpenAI · Rilascio 2025-08-07
81.9
punteggio medio
$1.25/1M
Prezzo Input
$10.00/1M
Prezzo Output
128K tokens (~64 books)
Finestra di Contesto
multimodal
Tipo
Tested on 7 benchmarks with 81.9% average. Top scores: Chatbot Arena Elo — Overall (1426.0%), Aider polyglot (88.0%), HELM — IFEval (87.5%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1426.0 | |
| Aider polyglot | coding | 88.0 | |
| HELM — IFEval | language | 87.5 | |
| HELM — MMLU-Pro | knowledge | 86.3 | |
| HELM — WildBench | reasoning | 85.7 | |
| HELM — GPQA | knowledge | 79.1 | |
| HELM — Omni-MATH | math | 64.7 |
Modelli Simili
Anthropic
81.8
Alibaba Qwen
78.4
DeepSeek
78.2
Anthropic
78.0