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
1gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
174,07 tok/s TG
Prefill 1.206 · TTFT 16.925 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMllamacpp
2gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
156,49 tok/s TG
Prefill 182 · TTFT 97.092 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMllama.cpp q3_k_m, q4-kv
3gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
81,35 tok/s TG
Prefill 998 · TTFT 9.924 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMllamacpp
4gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
74,79 tok/s TG
Prefill 1.062 · TTFT 9.322 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMllama.cpp q3_k_m, q4-kv
5gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
30,10 tok/s TG
Prefill 1.020 · TTFT 1.964 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMllama.cpp q3_k_m, q4-kv
6gemma-4-31B-it31BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
28,74 tok/s TG
Prefill 938 · TTFT 2.110 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMllamacpp