🏆
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) | 79,45 tok/s TG Prefill 744 · TTFT 13.292 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_0 | Details → | |
| 2 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 77,67 tok/s TG Prefill 745 · TTFT 13.316 ms | 5× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_0 | Details → | |
| 3 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 76,33 tok/s TG Prefill 877 · TTFT 23.278 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_0 | Details → | |
| 4 | Gemma-4-26B-A4B-it26BGoogle Harness benchmarkTool Usage Standard 1.0 | 2.268 Pkt 76,1% · 16/16 Aufg. · 347,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 5 | Gemma-4-26B-A4B-it26BGoogle Harness benchmarkTool Usage Standard 1.0 | 2.197 Pkt 73,7% · 16/16 Aufg. · 375,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | openclaw_cli | Details → | |
| 6 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 73,65 tok/s TG Prefill 843 · TTFT 24.099 ms | 10× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_0 | Details → | |
| 7 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkPerformancetest Small 1.0 | 42,22 tok/s TG Prefill 71 · TTFT 609 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 8 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 39,53 tok/s TG Prefill 282 · TTFT 6.994 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 9 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,81 tok/s TG Prefill 499 · TTFT 4.595 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_0 | Details → | |
| 10 | Gemma-4-26B-A4B-it26BGoogle Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 32,39 tok/s TG Prefill 665 · TTFT 2.992 ms | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ4_0 | Details → | |
| 11 | Gemma-4-26B-A4B-it26BGoogle Harness benchmarkGodBrain MCP Deep 40 - Wissensbasis-Lebenszyklus 1.0 | 2.271 Pkt 30,0% · 18/40 Aufg. · 982,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 12 | Gemma-4-26B-A4B-it26BGoogle Harness benchmarkTool-Parcours Dossier 40 V1.0 | 1.489 Pkt 25,0% · 22/40 Aufg. · 8.783,0 s | 1× | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → |