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
1Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
397,18 tok/s TG
Prefill 3.476 · TTFT 5.916 ms
10×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMopenclaw_cli
2Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
287,13 tok/s TG
Prefill 3.082 · TTFT 3.211 ms
5×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMopenclaw_cli
3Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation)
125,87 tok/s TG
Prefill 3.206 · TTFT 618 ms
1×NVIDIA GeForce RTX 3090 TiAMD Ryzen 5 5600X 6-Core Processor · 30 GB RAMopenclaw_cli