🏆
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 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 492,83 tok/s TG Prefill 1.231 · TTFT 103.873 ms | 10× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 2 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 420,20 tok/s TG Prefill 656 · TTFT 131.641 ms | 10× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | stratagodclawUD-IQ4_XS | Details → | |
| 3 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 246,45 tok/s TG Prefill 1.171 · TTFT 47.068 ms | 5× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 4 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 211,19 tok/s TG Prefill 592 · TTFT 60.940 ms | 5× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | stratagodclawUD-IQ4_XS | Details → | |
| 5 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,39 tok/s TG Prefill 3.269 · TTFT 6.004 ms | 10× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | vLLMgodclawNVFP4 | Details → | |
| 6 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 88,87 tok/s TG Prefill 1.120 · TTFT 20.453 ms | 10× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawIQ3_XXS | Details → | |
| 7 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 82,45 tok/s TG Prefill 2.547 · TTFT 3.826 ms | 5× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | vLLMgodclawNVFP4 | Details → | |
| 8 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 66,02 tok/s TG Prefill 838 · TTFT 12.155 ms | 5× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawIQ3_XXS | Details → | |
| 9 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,88 tok/s TG Prefill 909 · TTFT 2.194 ms | 1× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 10 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 41,83 tok/s TG Prefill 301 · TTFT 8.495 ms | 1× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | stratagodclawUD-IQ4_XS | Details → | |
| 11 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 36,38 tok/s TG Prefill 714 · TTFT 2.760 ms | 1× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | llama.cppgodclawIQ3_XXS | Details → | |
| 12 | Qwen3.8-Flash-Next180BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 25,26 tok/s TG Prefill 1.798 · TTFT 1.074 ms | 1× | NVIDIA GB10 (DGX Spark) iNVIDIA Grace · 120 GB RAM | vLLMgodclawNVFP4 | Details → |