🏆
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 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 1.481,23 tok/s TG Prefill 8.109 · TTFT 7.868 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 2 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 812,21 tok/s TG Prefill 7.214 · TTFT 2.650 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → | |
| 3 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 258,48 tok/s TG Prefill 5.318 · TTFT 363 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | llama.cppgodclawUD-Q4_K_M | Details → |

