🏆
Ranglisten
LLM Leaderboard
Reale Messergebnisse aller getesteten Sprachmodelle auf echter, benannter Hardware – bewertet nach roher Geschwindigkeit (Performance in Token pro Sekunde, Prefill und Zeit bis zum ersten Token) und nach praktischer Aufgaben-Qualität in vollständigen Agenten- und Chat-Abläufen (Harness). Wähle unten einen Benchmark-Typ oder filtere nach Modell, Hersteller und Hardware, um genau zu sehen, was jeweils geprüft wird und wie die Ergebnisse zustande kommen.
⚡ Performance (tok/s)🤖 Harness-Qualität👥 Concurrency🖥️ echte Hardware
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.890,69 tok/s TG Prefill 14.771 · TTFT 5.489 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 2 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.386,79 tok/s TG Prefill 19.981 · TTFT 1.205 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 3 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.295,30 tok/s TG Prefill 25.462 · TTFT 808 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 4 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.113,52 tok/s TG Prefill 13.157 · TTFT 1.764 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 5 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 848,28 tok/s TG Prefill 12.860 · TTFT 769 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 6 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 803,96 tok/s TG Prefill 16.236 · TTFT 616 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 7 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 787,90 tok/s TG Prefill 14.843 · TTFT 1.365 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 8 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 784,45 tok/s TG Prefill 17.724 · TTFT 560 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 9 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 763,58 tok/s TG Prefill 14.721 · TTFT 1.432 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 10 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 669,44 tok/s TG Prefill 11.783 · TTFT 840 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 11 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 404,59 tok/s TG Prefill 8.241 · TTFT 257 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 12 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 388,85 tok/s TG Prefill 2.378 · TTFT 1.888 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 13 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 388,20 tok/s TG Prefill 8.415 · TTFT 240 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 14 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 280,15 tok/s TG Prefill 9.224 · TTFT 217 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 15 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 267,04 tok/s TG Prefill 7.273 · TTFT 272 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → | |
| 16 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,31 tok/s TG Prefill 654 · TTFT 34.975 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 17 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,85 tok/s TG Prefill 481 · TTFT 21.081 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → | |
| 18 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,79 tok/s TG Prefill 406 · TTFT 4.916 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cli | Details → |