🏆
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 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 9,12 tok/s TG Prefill 94 · TTFT 251.044 ms | 10× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 2 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,91 tok/s TG Prefill 73 · TTFT 29.342 ms | 1× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 4,18 tok/s TG Prefill 10 · TTFT 226.444 ms | 1× | 2x NVIDIA GeForce RTX 20604x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 4 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 3,55 tok/s TG Prefill 77 · TTFT 144.723 ms | 5× | 2x AMD Radeon RX 7900 XTX i4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | GLM-4.5-Air106BZ.ai (Zhipu) Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 2,13 tok/s TG Prefill 18 · TTFT 117.963 ms | 1× | Keine GPU (CPU-only)4x Intel(R) Xeon(R) CPU E5-4620 v2 @ 2.60GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → |