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
1gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
18,07 tok/s TG
Prefill 96 · TTFT 20.531 ms
1×NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAMllama.cppgodclawQ4_K_M
2gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
42,26 tok/s TG
Prefill 170 · TTFT 234.298 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
3gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
30,26 tok/s TG
Prefill 149 · TTFT 103.687 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
4gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
12,57 tok/s TG
Prefill 137 · TTFT 14.433 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
5gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
13,32 tok/s TG
Prefill 405 · TTFT 26.375 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cli
6gpt-oss-120b120BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
6,46 tok/s TG
Prefill 333 · TTFT 6.064 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMvLLMcodex_cli