🏆
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 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 182,87 tok/s TG Prefill 7.295 · TTFT 5.014 ms | 10× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 2 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 146,91 tok/s TG Prefill 4.736 · TTFT 2.900 ms | 5× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → | |
| 3 | Qwen3-Coder-30B-A3B-Instruct30BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 86,23 tok/s TG Prefill 2.963 · TTFT 824 ms | 1× | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | llama.cppopenclaw_cliQ4_K_M | Details → |