🏆
Rankings
LLM Leaderboard
Real measurements of every tested language model on real, named hardware – rated by raw speed (performance in tokens per second, prefill and time to first token) and by practical task quality in complete agent and chat runs (harness). Pick a benchmark type below or filter by model, maker and hardware to see exactly what is tested and how the results are produced.
⚡ Performance (tok/s)🤖 Harness quality👥 Concurrency🖥️ real hardware
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 548,62 tok/s TG Prefill 4.931 · TTFT 20.370 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 2 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 530,51 tok/s TG Prefill 4.240 · TTFT 21.543 ms | 10× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 3 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 312,31 tok/s TG Prefill 4.491 · TTFT 6.623 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 4 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 305,98 tok/s TG Prefill 3.962 · TTFT 7.171 ms | 5× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 5 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,80 tok/s TG Prefill 1.953 · TTFT 1.180 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 6 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 112,58 tok/s TG Prefill 2.290 · TTFT 1.014 ms | 1× | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 7 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 14,51 tok/s TG Prefill 104 · TTFT 153.543 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 8 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,89 tok/s TG Prefill 103 · TTFT 154.280 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 9 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 12,34 tok/s TG Prefill 103 · TTFT 154.375 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 10 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,03 tok/s TG Prefill 49 · TTFT 47.605 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 11 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,97 tok/s TG Prefill 41 · TTFT 59.968 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 12 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,96 tok/s TG Prefill 41 · TTFT 60.147 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 13 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,62 tok/s TG Prefill 104 · TTFT 186.906 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 14 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 8,38 tok/s TG Prefill 105 · TTFT 186.362 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 15 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,29 tok/s TG Prefill 105 · TTFT 186.321 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 16 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 7,06 tok/s TG Prefill 266 · TTFT 8.622 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 17 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,61 tok/s TG Prefill 717 · TTFT 35.394 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 18 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,92 tok/s TG Prefill 600 · TTFT 23.512 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 19 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,00 tok/s TG Prefill 139 · TTFT 15.493 ms | 1× | 3x AMD Radeon AI PRO R9700 iAMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 20 | MiniMax-M2.7230BMiniMax Performance benchmark | 3,00 tok/s TG Prefill 139 · TTFT 15.493 ms | 1× | 3x AMD Radeon AI PRO R9700 i32x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → |