🏆
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 | minimax-m2.5-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 105,57 tok/s TG Prefill 6.997 · TTFT 5.319 ms | 10× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 2 | minimax-m2.5-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,44 tok/s TG Prefill 5.550 · TTFT 2.628 ms | 5× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 3 | minimax-m2.5-awq230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,93 tok/s TG Prefill 2.096 · TTFT 1.093 ms | 1× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → |

