🏆
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.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,17 tok/s TG Prefill 41 · TTFT 216.967 ms | 10× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 2 | Laguna-M.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,03 tok/s TG Prefill 42 · TTFT 216.252 ms | 5× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → | |
| 3 | Laguna-M.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 0,30 tok/s TG Prefill 29 · TTFT 74.552 ms | 1× | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAM | llama.cppcodex_cliQ4_K_M | Details → |