🏆
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) | 103,82 tok/s TG Prefill 1.501 · TTFT 14.918 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 101,67 tok/s TG Prefill 1.142 · TTFT 8.725 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | Qwen-AgentWorld-35B-A3B35BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 53,72 tok/s TG Prefill 1.018 · TTFT 1.900 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_K_M | Details → |