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
1Qwen3.8-27B27.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
117,36 tok/s TG
Prefill 1.455 · TTFT 15.755 ms
10×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
2Qwen3.8-27B27.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
64,07 tok/s TG
Prefill 985 · TTFT 10.349 ms
5×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M
3Qwen3.8-27B27.8BQwen (Alibaba) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
26,39 tok/s TG
Prefill 886 · TTFT 2.232 ms
1×AMD Radeon AI PRO R9700AMD Ryzen 3 3100 4-Core Processor · 31 GB RAMllama.cppopenclaw_cliQ4_K_M