🏆
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 | Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,97 tok/s TG Prefill 45 · TTFT 191.746 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,20 tok/s TG Prefill 50 · TTFT 181.487 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,63 tok/s TG Prefill 53 · TTFT 50.822 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 5,77 tok/s TG Prefill 48 · TTFT 182.972 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,80 tok/s TG Prefill 49 · TTFT 183.700 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → |

