🏆
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-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.757,37 tok/s TG Prefill 9.025 · TTFT 7.343 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-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.753,82 tok/s TG Prefill 9.267 · TTFT 7.329 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.740,43 tok/s TG Prefill 9.653 · TTFT 7.258 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 975,10 tok/s TG Prefill 7.343 · TTFT 2.879 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 967,89 tok/s TG Prefill 8.250 · TTFT 2.709 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 966,13 tok/s TG Prefill 8.310 · TTFT 2.703 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 310,19 tok/s TG Prefill 5.706 · TTFT 484 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,93 tok/s TG Prefill 4.887 · TTFT 562 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 9 | Laguna-XS-2.1Poolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 309,54 tok/s TG Prefill 5.382 · TTFT 511 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawQ4_K_M | Details → |