🏆
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 | Kolibri-178.1BAleph Alpha Performance benchmarkKolibri Prefill-Decode 1024-256 - Summenraten C1 C5 C10 V1 | 1.044,38 tok/s TG Prefill 38.866 · TTFT 388 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | serverphasetimingNVFP4 | Details → | |
| 2 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 902,92 tok/s TG Prefill - · TTFT 227 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 3 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 846,62 tok/s TG Prefill - · TTFT 238 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 4 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 833,03 tok/s TG Prefill - · TTFT 213 ms | 10× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 5 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 626,30 tok/s TG Prefill - · TTFT 165 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 6 | Kolibri-178.1BAleph Alpha Performance benchmarkKolibri Prefill-Decode 1024-256 - Summenraten C1 C5 C10 V1 | 589,64 tok/s TG Prefill 43.711 · TTFT 223 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | serverphasetimingNVFP4 | Details → | |
| 7 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 569,97 tok/s TG Prefill - · TTFT 160 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 8 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 490,51 tok/s TG Prefill - · TTFT 177 ms | 5× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 9 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 171,47 tok/s TG Prefill - · TTFT 98 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 10 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 168,71 tok/s TG Prefill - · TTFT 160 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 11 | Kolibri-178.1BAleph Alpha Performance benchmarkKolibri Prefill-Decode 1024-256 - Summenraten C1 C5 C10 V1 | 158,18 tok/s TG Prefill 2.213 · TTFT 6.611 ms | 10× | AMD Radeon 8060S Graphics iAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | serverphasetimingQ4_K_M | Details → | |
| 12 | Kolibri-178.1BAleph Alpha Performance benchmarkKolibri Prefill-Decode 1024-256 - Summenraten C1 C5 C10 V1 | 133,13 tok/s TG Prefill 20.590 · TTFT 106 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | serverphasetimingNVFP4 | Details → | |
| 13 | Kolibri-178.1BAleph Alpha Performance benchmarkTimebench 3 - Kombi (Prefill + Generation) | 130,86 tok/s TG Prefill - · TTFT 155 ms | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMgodclaw | Details → | |
| 14 | Kolibri-178.1BAleph Alpha Performance benchmarkKolibri Prefill-Decode 1024-256 - Summenraten C1 C5 C10 V1 | 126,83 tok/s TG Prefill 1.426 · TTFT 3.664 ms | 5× | AMD Radeon 8060S Graphics iAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | serverphasetimingQ4_K_M | Details → | |
| 15 | Kolibri-178.1BAleph Alpha Harness benchmarkOffice Agentic Work 100 - Tool Usage V1 | 100 Pkt 100,0% · 100/100 Aufg. · 547,7 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | officeagentic100NVFP4 | Details → | |
| 16 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-Qwen Diverse Deterministic 210 V1.0 | 207 Pkt 98,6% · 207/210 Aufg. · 1.080,2 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic210 | Details → | |
| 17 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 289 Pkt 93,2% · 289/310 Aufg. · 2.504,7 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310FP8 | Details → | |
| 18 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 283 Pkt 91,3% · 283/310 Aufg. · 2.384,4 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310NVFP4 | Details → | |
| 19 | Kolibri-178.1BAleph Alpha Performance benchmarkKolibri Prefill-Decode 1024-256 - Summenraten C1 C5 C10 V1 | 55,83 tok/s TG Prefill 1.304 · TTFT 810 ms | 1× | AMD Radeon 8060S Graphics iAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | serverphasetimingQ4_K_M | Details → | |
| 20 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-Qwen Diverse Deterministic 210 V1.0 | 108 Pkt 51,4% · 108/210 Aufg. · 72,1 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic210 | Details → | |
| 21 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 119 Pkt 38,4% · 119/310 Aufg. · 87,9 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310NVFP4 | Details → | |
| 22 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 115 Pkt 37,1% · 115/310 Aufg. · 99,6 s | 1× | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310FP8 | Details → |