Created bymario-alka.dePowered bygodcore.denoob2claw.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
1MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,37 tok/s TG
Prefill 62 · TTFT 36.988 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
2MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
4,32 tok/s TG
Prefill 61 · TTFT 37.512 ms
1×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
3MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,93 tok/s TG
Prefill 94 · TTFT 112.413 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
4MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,16 tok/s TG
Prefill 89 · TTFT 115.055 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
5MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
3,01 tok/s TG
Prefill 89 · TTFT 114.283 ms
10×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M
6MiniMax-M2.5230BMiniMax Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
2,72 tok/s TG
Prefill 92 · TTFT 114.221 ms
5×NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 126 GB RAMllama.cppcodex_cliQ4_K_M