🏆
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 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 156,96 tok/s TG Prefill 1.527 · TTFT 53.069 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,91 tok/s TG Prefill 1.782 · TTFT 56.458 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 134,85 tok/s TG Prefill 1.762 · TTFT 56.409 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,39 tok/s TG Prefill 1.607 · TTFT 59.457 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 100,02 tok/s TG Prefill 1.095 · TTFT 81.153 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 95,47 tok/s TG Prefill 3.802 · TTFT 14.501 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 7 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,04 tok/s TG Prefill 3.584 · TTFT 15.347 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 8 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,30 tok/s TG Prefill 1.360 · TTFT 19.580 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,81 tok/s TG Prefill 1.650 · TTFT 19.200 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 10 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,06 tok/s TG Prefill 1.465 · TTFT 20.463 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,39 tok/s TG Prefill 1.650 · TTFT 21.020 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,67 tok/s TG Prefill 2.956 · TTFT 8.171 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 13 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,74 tok/s TG Prefill 2.800 · TTFT 8.614 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 14 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 55,78 tok/s TG Prefill 943 · TTFT 29.082 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 15 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 51,73 tok/s TG Prefill 786 · TTFT 142.996 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,65 tok/s TG Prefill 687 · TTFT 48.937 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,90 tok/s TG Prefill 1.418 · TTFT 2.451 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 18 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,08 tok/s TG Prefill 1.597 · TTFT 2.166 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 19 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,82 tok/s TG Prefill 1.534 · TTFT 2.252 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,73 tok/s TG Prefill 1.485 · TTFT 2.328 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,74 tok/s TG Prefill 1.143 · TTFT 3.036 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 17,11 tok/s TG Prefill 1.404 · TTFT 2.484 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 23 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,83 tok/s TG Prefill 1.326 · TTFT 2.635 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 24 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,81 tok/s TG Prefill 173 · TTFT 10.910 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,80 tok/s TG Prefill 638 · TTFT 5.420 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,49 tok/s TG Prefill 208 · TTFT 86.235 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,67 tok/s TG Prefill 99 · TTFT 85.963 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 6,57 tok/s TG Prefill 98 · TTFT 86.763 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,84 tok/s TG Prefill 171 · TTFT 107.858 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,18 tok/s TG Prefill 91 · TTFT 93.827 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 31 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,11 tok/s TG Prefill 85 · TTFT 100.325 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 32 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,24 tok/s TG Prefill 60 · TTFT 141.349 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 33 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,24 tok/s TG Prefill 57 · TTFT 150.218 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 34 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,21 tok/s TG Prefill 294 · TTFT 11.834 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,16 tok/s TG Prefill 128 · TTFT 21.272 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,65 tok/s TG Prefill 252 · TTFT 13.838 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1,35 tok/s TG Prefill 94 · TTFT 22.587 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 38 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,66 tok/s TG Prefill 62 · TTFT 34.310 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 39 | command-a-reasoning-08-2025111BCohere PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,02 tok/s TG Prefill 5 · TTFT 485.856 ms | 1× | Intel Arc Pro B70AMD Ryzen 9 7945HX with Radeon Graphics · 29 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |