🏆
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 | Qwen2.5-32B-Instruct32.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 473,96 tok/s TG Prefill 5.347 · TTFT 21.026 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawAWQ | Details → | |
| 2 | Qwen2.5-32B-Instruct32.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 250,73 tok/s TG Prefill 5.071 · TTFT 5.931 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawAWQ | Details → | |
| 3 | Qwen2.5-32B-Instruct32.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 68,44 tok/s TG Prefill 3.289 · TTFT 747 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawAWQ | Details → | |
| 4 | Qwen2.5-32B-Instruct32.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 510,34 tok/s TG Prefill 6.104 · TTFT 4.473 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 5 | Qwen2.5-32B-Instruct32.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 300,61 tok/s TG Prefill 4.931 · TTFT 2.537 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → | |
| 6 | Qwen2.5-32B-Instruct32.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 71,16 tok/s TG Prefill 2.321 · TTFT 1.217 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclawAWQ | Details → |

