🏆
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 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,60 tok/s TG Prefill 3.450 · TTFT 2.889 ms | 5× | Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 2 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,88 tok/s TG Prefill 2.354 · TTFT 9.328 ms | 10× | Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 3 | gpt-oss-20b20BOpenAI Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 132,28 tok/s TG Prefill 2.178 · TTFT 988 ms | 1× | Tesla V100-PCIE-32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → |