🏆
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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.253,31 tok/s TG Prefill 5.076 · TTFT 10.589 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.147,50 tok/s TG Prefill 5.750 · TTFT 10.762 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.141,98 tok/s TG Prefill 6.489 · TTFT 10.511 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.133,50 tok/s TG Prefill 5.539 · TTFT 11.093 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.089,34 tok/s TG Prefill 4.323 · TTFT 12.397 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 726,51 tok/s TG Prefill 4.456 · TTFT 4.078 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 652,22 tok/s TG Prefill 5.743 · TTFT 3.727 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 → | |
| 8 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 646,89 tok/s TG Prefill 4.828 · TTFT 4.104 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 → | |
| 9 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 644,40 tok/s TG Prefill 3.769 · TTFT 4.755 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 629,83 tok/s TG Prefill 26.016 · TTFT 1.347 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 11 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 629,69 tok/s TG Prefill 5.452 · TTFT 3.844 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 587,94 tok/s TG Prefill 22.877 · TTFT 1.531 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 13 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 514,52 tok/s TG Prefill 22.477 · TTFT 1.541 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 14 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 487,01 tok/s TG Prefill 20.068 · TTFT 1.732 ms | 10× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 15 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 410,37 tok/s TG Prefill 19.698 · TTFT 777 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 16 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 378,00 tok/s TG Prefill 17.176 · TTFT 892 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 17 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 365,08 tok/s TG Prefill 17.147 · TTFT 895 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 18 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 342,54 tok/s TG Prefill 15.132 · TTFT 1.011 ms | 5× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 19 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 242,22 tok/s TG Prefill 2.455 · TTFT 1.020 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 218,39 tok/s TG Prefill 2.921 · TTFT 833 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,49 tok/s TG Prefill 3.668 · TTFT 663 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 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,08 tok/s TG Prefill 4.069 · TTFT 599 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 → | |
| 23 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 215,33 tok/s TG Prefill 3.303 · TTFT 754 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 → | |
| 24 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 146,76 tok/s TG Prefill 6.990 · TTFT 350 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 25 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 133,13 tok/s TG Prefill 8.147 · TTFT 302 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 26 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 132,39 tok/s TG Prefill 6.364 · TTFT 383 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawFP8 | Details → | |
| 27 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 123,21 tok/s TG Prefill 7.332 · TTFT 334 ms | 1× | 2x NVIDIA RTX A6000AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 28 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 107,02 tok/s TG Prefill 457 · TTFT 125.537 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 29 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,05 tok/s TG Prefill 361 · TTFT 137.879 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,68 tok/s TG Prefill 193 · TTFT 220.912 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 78,23 tok/s TG Prefill 354 · TTFT 169.650 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 32 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,25 tok/s TG Prefill 192 · TTFT 223.583 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,95 tok/s TG Prefill 193 · TTFT 224.160 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 64,58 tok/s TG Prefill 300 · TTFT 56.560 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,39 tok/s TG Prefill 2.142 · TTFT 1.132 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmark | 62,39 tok/s TG Prefill 2.142 · TTFT 1.132 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 37 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,99 tok/s TG Prefill 2.410 · TTFT 1.005 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmark | 60,99 tok/s TG Prefill 2.410 · TTFT 1.005 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawQ4_K_M | Details → | |
| 39 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 60,63 tok/s TG Prefill 390 · TTFT 48.367 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 40 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,48 tok/s TG Prefill 158 · TTFT 97.895 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 41 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,26 tok/s TG Prefill 157 · TTFT 98.597 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 42 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 48,00 tok/s TG Prefill 156 · TTFT 99.137 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 43 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 45,84 tok/s TG Prefill 299 · TTFT 64.947 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 44 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 38,54 tok/s TG Prefill 2.124 · TTFT 1.146 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | vLLMgodclawFP8 | Details → | |
| 45 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,83 tok/s TG Prefill 267 · TTFT 9.108 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 46 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,73 tok/s TG Prefill 2.230 · TTFT 1.115 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 47 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmark | 22,73 tok/s TG Prefill 2.230 · TTFT 1.115 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 48 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,53 tok/s TG Prefill 2.237 · TTFT 1.117 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | vLLMgodclawAWQ | Details → | |
| 49 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmark | 22,53 tok/s TG Prefill 2.237 · TTFT 1.117 ms | 1× | 3x AMD Radeon AI PRO R970032x AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | godclawAWQ | Details → | |
| 50 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 22,07 tok/s TG Prefill 348 · TTFT 6.984 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 51 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,33 tok/s TG Prefill 127 · TTFT 19.200 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 52 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 20,05 tok/s TG Prefill 127 · TTFT 19.170 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 53 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 19,96 tok/s TG Prefill 128 · TTFT 19.123 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 54 | Qwen3-Coder-NextQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 18,14 tok/s TG Prefill 279 · TTFT 8.732 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → |