🏆
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-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 174,20 tok/s TG Prefill 5.042 · TTFT 47.620 ms | 10× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 2 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 106,12 tok/s TG Prefill 5.634 · TTFT 12.854 ms | 5× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 3 | MiniMax-M2.7230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 31,52 tok/s TG Prefill 2.328 · TTFT 991 ms | 1× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 4 | MiniMax-M2.7230BMiniMax Harness benchmarkTool Usage Standard 1.0 | 858 Pkt 28,8% · 16/16 Aufg. · 1.222,0 s | 1× | NVIDIA DGX SPARK (GB10)NVIDIA Grace · 120 GB RAM | godclawAWQ-4BIT | Details → |

