🏆
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-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 150,36 tok/s TG Prefill 1.880 · TTFT 17.241 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 2 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,94 tok/s TG Prefill 4.212 · TTFT 8.113 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 3 | Mistral-Small-3.1-24B-Instruct-250324BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,99 tok/s TG Prefill 2.572 · TTFT 12.677 ms | 10× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 4 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 119,65 tok/s TG Prefill 1.469 · TTFT 9.597 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 5 | Mistral-Small-3.1-24B-Instruct-250324BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 116,54 tok/s TG Prefill 1.812 · TTFT 19.077 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 6 | Mistral-Small-3.1-24B-Instruct-250324BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 89,49 tok/s TG Prefill 2.131 · TTFT 6.932 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 7 | Mistral-Small-3.1-24B-Instruct-250324BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,25 tok/s TG Prefill 12.250 · TTFT 2.840 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 8 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,59 tok/s TG Prefill 2.675 · TTFT 5.037 ms | 5× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 9 | Mistral-Small-3.1-24B-Instruct-250324BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,55 tok/s TG Prefill 1.346 · TTFT 10.549 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 10 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,09 tok/s TG Prefill 883 · TTFT 2.603 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 11 | Mistral-Small-3.1-24B-Instruct-250324BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 44,99 tok/s TG Prefill 8.091 · TTFT 1.621 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 12 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,97 tok/s TG Prefill 1.640 · TTFT 1.400 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 13 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 33,10 tok/s TG Prefill 1.265 · TTFT 1.767 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 14 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performancebenchmark i | 33,10 tok/s TG Prefill 1.265 · TTFT 1.767 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 15 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 32,98 tok/s TG Prefill 2.592 · TTFT 790 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 16 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performancebenchmark i | 32,98 tok/s TG Prefill 2.592 · TTFT 790 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 17 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 31,27 tok/s TG Prefill 1.563 · TTFT 1.699 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 18 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performancebenchmark i | 31,27 tok/s TG Prefill 1.563 · TTFT 1.699 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 19 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,25 tok/s TG Prefill 939 · TTFT 14.944 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 20 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 29,97 tok/s TG Prefill 1.536 · TTFT 2.083 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 21 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performancebenchmark i | 29,97 tok/s TG Prefill 1.536 · TTFT 2.083 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 22 | Mistral-Small-3.1-24B-Instruct-250324BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,14 tok/s TG Prefill 784 · TTFT 2.931 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 23 | Mistral-Small-3.1-24B-Instruct-250324BQ8_0Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 28,79 tok/s TG Prefill 1.195 · TTFT 1.920 ms | 1× | 2x AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclaw | Details → | |
| 24 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 28,76 tok/s TG Prefill 1.407 · TTFT 1.945 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclaw | Details → | |
| 25 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI Performancebenchmark i | 28,76 tok/s TG Prefill 1.407 · TTFT 1.945 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 26 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 26,03 tok/s TG Prefill 1.200 · TTFT 27.883 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclaw | Details → | |
| 27 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 23,84 tok/s TG Prefill 277 · TTFT 48.247 ms | 5× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 28 | Mistral-Small-3.1-24B-Instruct-250324BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 15,00 tok/s TG Prefill 9.072 · TTFT 245 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 29 | Mistral-Small-3.1-24B-Instruct-250324BINT4Mistral AI Performancebenchmark i | 15,00 tok/s TG Prefill 9.072 · TTFT 245 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 30 | Mistral-Small-3.1-24B-Instruct-250324BQ4_K_MMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 13,57 tok/s TG Prefill 159 · TTFT 13.491 ms | 1× | NVIDIA Tesla P100 PCIe 16GBAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | llama.cppopenclaw_cli | Details → | |
| 31 | Mistral-Small-3.1-24B-Instruct-250324BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,99 tok/s TG Prefill 4.687 · TTFT 495 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 32 | Mistral-Small-3.1-24B-Instruct-250324BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 6,98 tok/s TG Prefill 4.076 · TTFT 559 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 33 | Mistral-Small-3.1-24B-Instruct-250324BINT4Mistral AI Performancebenchmark i | 6,98 tok/s TG Prefill 4.076 · TTFT 559 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → | |
| 34 | Mistral-Small-3.1-24B-Instruct-250324BAWQMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) i | 6,13 tok/s TG Prefill 2.944 · TTFT 763 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclaw | Details → | |
| 35 | Mistral-Small-3.1-24B-Instruct-250324BINT4Mistral AI Performancebenchmark i | 6,13 tok/s TG Prefill 2.944 · TTFT 763 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclaw | Details → |
