🏆
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 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 959,57 tok/s TG Prefill 8.078 · TTFT 11.971 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 2 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 544,25 tok/s TG Prefill 6.975 · TTFT 4.321 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 3 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 189,78 tok/s TG Prefill 4.035 · TTFT 667 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 4 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,26 tok/s TG Prefill 284 · TTFT 238.161 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 5 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,52 tok/s TG Prefill 351 · TTFT 222.335 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketUD-Q4_K_M | Details → | |
| 6 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,52 tok/s TG Prefill 2.053 · TTFT 1.304 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 7 | Mistral-Small-4-119B-2603119BMistral AI Performancebenchmark | 58,52 tok/s TG Prefill 2.053 · TTFT 1.304 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 8 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,18 tok/s TG Prefill 234 · TTFT 253.628 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 9 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,16 tok/s TG Prefill 233 · TTFT 253.701 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 10 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,98 tok/s TG Prefill 229 · TTFT 232.955 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 11 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 39,36 tok/s TG Prefill 221 · TTFT 103.372 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 12 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,54 tok/s TG Prefill 233 · TTFT 92.559 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketUD-Q4_K_M | Details → | |
| 13 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,27 tok/s TG Prefill 151 · TTFT 124.312 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 14 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,14 tok/s TG Prefill 155 · TTFT 122.915 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 15 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 34,65 tok/s TG Prefill 166 · TTFT 119.631 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 16 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,66 tok/s TG Prefill 203 · TTFT 281.308 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliUD-Q4_K_M | Details → | |
| 17 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 21,61 tok/s TG Prefill 202 · TTFT 281.424 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliUD-Q4_K_M | Details → | |
| 18 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,00 tok/s TG Prefill 149 · TTFT 156.524 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliUD-Q4_K_M | Details → | |
| 19 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,68 tok/s TG Prefill 190 · TTFT 152.266 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliUD-Q4_K_M | Details → | |
| 20 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,70 tok/s TG Prefill 135 · TTFT 20.068 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 21 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,23 tok/s TG Prefill 111 · TTFT 24.534 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 22 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,20 tok/s TG Prefill 112 · TTFT 24.250 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 23 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 15,13 tok/s TG Prefill 108 · TTFT 25.093 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 24 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,47 tok/s TG Prefill 190 · TTFT 14.242 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketUD-Q4_K_M | Details → | |
| 25 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,71 tok/s TG Prefill 117 · TTFT 23.115 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliUD-Q4_K_M | Details → | |
| 26 | Mistral-Small-4-119B-2603119BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,77 tok/s TG Prefill 325 · TTFT 5.900 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | vLLMcodex_cliAWQ | Details → |