🏆
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
| # | Model / Maker | Metrics | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | Gemma-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 RAM | openclaw_cli | Details → | |
| 2 | Gemma-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 RAM | openclaw_cli | Details → | |
| 3 | Gemma-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 RAM | openclaw_cli | Details → |

