🏆
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 | gemma-4-E2B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.608,46 tok/s TG Prefill 31.452 · TTFT 1.633 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 2 | gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.022,79 tok/s TG Prefill 18.744 · TTFT 2.204 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 3 | gemma-4-E2B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 973,54 tok/s TG Prefill 23.599 · TTFT 460 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 4 | gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 616,01 tok/s TG Prefill 13.778 · TTFT 803 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 5 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 497,64 tok/s TG Prefill 8.340 · TTFT 5.360 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 6 | gemma-4-12B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 486,20 tok/s TG Prefill 4.345 · TTFT 5.863 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 7 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 318,66 tok/s TG Prefill 5.742 · TTFT 2.122 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 8 | gemma-4-12B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 315,66 tok/s TG Prefill 3.728 · TTFT 2.722 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 9 | gemma-4-E2B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 228,18 tok/s TG Prefill 11.075 · TTFT 179 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 10 | gemma-4-E4B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 144,58 tok/s TG Prefill 7.078 · TTFT 281 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 11 | Ministral-3-14B-Reasoning-2512Mistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 85,15 tok/s TG Prefill 3.218 · TTFT 666 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 12 | gemma-4-12B-itGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 75,04 tok/s TG Prefill 3.021 · TTFT 659 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 13 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,73 tok/s TG Prefill 816 · TTFT 35.129 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 14 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 30,59 tok/s TG Prefill 819 · TTFT 35.012 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 15 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 29,41 tok/s TG Prefill 1.525 · TTFT 19.257 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 16 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,73 tok/s TG Prefill 660 · TTFT 34.336 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 17 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,64 tok/s TG Prefill 1.305 · TTFT 10.957 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 18 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,13 tok/s TG Prefill 488 · TTFT 20.357 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 19 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,05 tok/s TG Prefill 517 · TTFT 20.708 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 20 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,94 tok/s TG Prefill 516 · TTFT 20.783 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 21 | Qwen3-VL-30B-A3B-InstructQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 16,34 tok/s TG Prefill 672 · TTFT 3.622 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 22 | gpt-oss-20bOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,29 tok/s TG Prefill 446 · TTFT 4.523 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclaw | Details → | |
| 23 | Qwen3.5-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,63 tok/s TG Prefill 345 · TTFT 5.672 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → | |
| 24 | Qwen3.6-35B-A3BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,61 tok/s TG Prefill 342 · TTFT 5.738 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | vLLMgodclawAWQ | Details → |