Created bymario-alka.dePowered bynoob2claw.detricoma.de
🏆
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
Reset
Metric:
#Model / MakerMetricsParallelGPU / CPU / RAMRuntime
1Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,97 tok/s TG
Prefill 45 · TTFT 191.746 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
2Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,20 tok/s TG
Prefill 50 · TTFT 181.487 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
3Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
2,63 tok/s TG
Prefill 53 · TTFT 50.822 ms
1×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
4Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
5,77 tok/s TG
Prefill 48 · TTFT 182.972 ms
10×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M
5Laguna-M.1225.8BPoolside Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,80 tok/s TG
Prefill 49 · TTFT 183.700 ms
5×NVIDIA RTX PRO 6000 Blackwell Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAMllama.cppgodclawQ4_K_M