🏆
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 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.799,41 tok/s TG Prefill 9.192 · TTFT 8.876 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 → | |
| 2 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.607,48 tok/s TG Prefill 7.448 · TTFT 7.492 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.556,71 tok/s TG Prefill 6.275 · TTFT 8.228 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 4 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.447,27 tok/s TG Prefill 8.138 · TTFT 7.915 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 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.400,99 tok/s TG Prefill 6.038 · TTFT 8.703 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 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 920,16 tok/s TG Prefill 3.818 · TTFT 13.771 ms | 10× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 7 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 882,70 tok/s TG Prefill 6.523 · TTFT 2.651 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 867,90 tok/s TG Prefill 5.424 · TTFT 2.985 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 9 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 794,89 tok/s TG Prefill 5.470 · TTFT 3.060 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 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 780,58 tok/s TG Prefill 7.221 · TTFT 2.850 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 → | |
| 11 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 762,69 tok/s TG Prefill 8.704 · TTFT 2.484 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 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 517,07 tok/s TG Prefill 3.355 · TTFT 4.929 ms | 5× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 13 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,02 tok/s TG Prefill 1.120 · TTFT 42.243 ms | 10× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 14 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 295,61 tok/s TG Prefill 3.556 · TTFT 542 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 15 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 292,74 tok/s TG Prefill 5.076 · TTFT 381 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 16 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 266,28 tok/s TG Prefill 4.441 · TTFT 434 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 → | |
| 17 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 264,61 tok/s TG Prefill 5.077 · TTFT 385 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 → | |
| 18 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 240,47 tok/s TG Prefill 5.000 · TTFT 386 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 → | |
| 19 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,85 tok/s TG Prefill 3.842 · TTFT 5.955 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,46 tok/s TG Prefill 2.663 · TTFT 8.403 ms | 10× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 21 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 210,36 tok/s TG Prefill 3.683 · TTFT 5.472 ms | 10× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,38 tok/s TG Prefill 940 · TTFT 16.001 ms | 5× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 23 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 184,15 tok/s TG Prefill 2.849 · TTFT 676 ms | 1× | NVIDIA GeForce RTX 3090 TiAMD Ryzen 9 8945HX with Radeon Graphics · 92 GB RAM | llama.cppwebsocketQ4_K_M | Details → | |
| 24 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 181,28 tok/s TG Prefill 3.620 · TTFT 2.799 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 25 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 179,04 tok/s TG Prefill 2.033 · TTFT 4.903 ms | 5× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 26 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 173,97 tok/s TG Prefill 3.522 · TTFT 2.513 ms | 5× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 27 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 104,78 tok/s TG Prefill 284 · TTFT 139.519 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 28 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,53 tok/s TG Prefill 283 · TTFT 140.845 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 29 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 103,11 tok/s TG Prefill 282 · TTFT 141.242 ms | 10× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 30 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 91,41 tok/s TG Prefill 1.698 · TTFT 1.137 ms | 1× | AMD Radeon PRO W7900 Dual SlotAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,58 tok/s TG Prefill 2.449 · TTFT 787 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 32 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 70,57 tok/s TG Prefill 2.415 · TTFT 713 ms | 1× | 4x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 33 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,03 tok/s TG Prefill 856 · TTFT 2.253 ms | 1× | NVIDIA GeForce RTX 5070 TiAMD Ryzen Threadripper PRO 5975WX 32-Cores · 247 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 34 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,81 tok/s TG Prefill 239 · TTFT 56.818 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 35 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,49 tok/s TG Prefill 238 · TTFT 57.323 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 36 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,07 tok/s TG Prefill 238 · TTFT 57.464 ms | 5× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 37 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,33 tok/s TG Prefill 200 · TTFT 9.642 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 38 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,10 tok/s TG Prefill 193 · TTFT 10.006 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 39 | Ornith-1.0-35B35BDeepReinforce Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 24,98 tok/s TG Prefill 199 · TTFT 9.735 ms | 1× | 3x AMD Radeon AI PRO R9700AMD Ryzen Threadripper PRO 7955WX 16-Cores · 184 GB RAM | llama.cppgodclawQ4_K_M | Details → |