🏆
Ranglisten
LLM Leaderboard
Reale Messergebnisse aller getesteten Sprachmodelle auf echter, benannter Hardware – bewertet nach roher Geschwindigkeit (Performance in Token pro Sekunde, Prefill und Zeit bis zum ersten Token) und nach praktischer Aufgaben-Qualität in vollständigen Agenten- und Chat-Abläufen (Harness). Wähle unten einen Benchmark-Typ oder filtere nach Modell, Hersteller und Hardware, um genau zu sehen, was jeweils geprüft wird und wie die Ergebnisse zustande kommen.
⚡ Performance (tok/s)🤖 Harness-Qualität👥 Concurrency🖥️ echte Hardware
| # | Modell / Hersteller | Messwerte | Parallel | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|---|
| 1 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 361,84 tok/s TG Prefill 7.233 · TTFT 2.750 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 2 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 353,85 tok/s TG Prefill 4.758 · TTFT 4.353 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 3 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 275,62 tok/s TG Prefill 6.734 · TTFT 1.481 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 4 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 255,41 tok/s TG Prefill 6.332 · TTFT 1.575 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 5 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 248,72 tok/s TG Prefill 3.178 · TTFT 5.437 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 6 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 225,93 tok/s TG Prefill 1.021 · TTFT 8.456 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 7 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 216,62 tok/s TG Prefill 1.136 · TTFT 15.201 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 8 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 206,60 tok/s TG Prefill 3.450 · TTFT 2.889 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 9 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 196,16 tok/s TG Prefill 860 · TTFT 118.321 ms | 10× | NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 10 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 193,56 tok/s TG Prefill 3.011 · TTFT 2.862 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 11 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 186,18 tok/s TG Prefill 1.748 · TTFT 10.113 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 12 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 139,86 tok/s TG Prefill 1.753 · TTFT 5.039 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 13 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 138,88 tok/s TG Prefill 2.354 · TTFT 9.328 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 14 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 137,92 tok/s TG Prefill 818 · TTFT 45.184 ms | 5× | NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 15 | gpt-oss-20b20BOpenAI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 132,28 tok/s TG Prefill 2.178 · TTFT 988 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 16 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 128,96 tok/s TG Prefill 4.924 · TTFT 402 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 17 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 122,55 tok/s TG Prefill 5.151 · TTFT 2.489 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 18 | gemma-4-E2B-it5BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 117,98 tok/s TG Prefill 5.227 · TTFT 378 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 19 | Qwen3.6-35B-A3B35BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 94,40 tok/s TG Prefill 768 · TTFT 2.243 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 20 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 93,40 tok/s TG Prefill 3.060 · TTFT 3.167 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 21 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 83,75 tok/s TG Prefill 1.512 · TTFT 1.139 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 22 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 83,10 tok/s TG Prefill 6.957 · TTFT 7.450 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 23 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 74,39 tok/s TG Prefill 1.748 · TTFT 11.355 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 24 | Meta-Llama-3.1-8B-Instruct8BMeta PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 69,93 tok/s TG Prefill 2.843 · TTFT 920 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 25 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 63,23 tok/s TG Prefill 904 · TTFT 15.542 ms | 5× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | strataIQ3_S | Details → | |
| 26 | Ornith-1.0-9B9BDeepReinforce PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 62,07 tok/s TG Prefill 2.204 · TTFT 932 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 27 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 61,09 tok/s TG Prefill 1.023 · TTFT 43.363 ms | 10× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | strataIQ3_S | Details → | |
| 28 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,28 tok/s TG Prefill 483 · TTFT 4.084 ms | 1× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | strataIQ3_S | Details → | |
| 29 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 59,02 tok/s TG Prefill 1.132 · TTFT 12.062 ms | 5× | NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 30 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 58,59 tok/s TG Prefill 1.147 · TTFT 1.541 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ4_K_M | Details → | |
| 31 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,78 tok/s TG Prefill 1.962 · TTFT 6.490 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 32 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,41 tok/s TG Prefill 1.260 · TTFT 19.903 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 33 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 52,11 tok/s TG Prefill 510 · TTFT 3.869 ms | 1× | NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 34 | Qwen3.8-Flash-Next180BQwen (Alibaba) PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,60 tok/s TG Prefill 468 · TTFT 4.250 ms | 1× | NVIDIA Tesla V100 PCIe 32GB iAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 29 GB RAM | stratagodclawIQ3_XXS | Details → | |
| 35 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 49,35 tok/s TG Prefill 778 · TTFT 25.706 ms | 10× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 36 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 47,87 tok/s TG Prefill 1.491 · TTFT 7.113 ms | 5× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 37 | gemma-4-12B-it12BGoogle PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 36,37 tok/s TG Prefill 928 · TTFT 13.981 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 38 | Ministral-3-14B-Reasoning-251214BMistral AI PerformancebenchmarkTimebench 3 - Kombi (Prefill + Generation) | 35,13 tok/s TG Prefill 2.320 · TTFT 975 ms | 1× | NVIDIA Tesla V100 PCIe 32GBAMD Ryzen 3 PRO 3200GE w/ Radeon Vega Graphics · 61 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 39 | Qwen2.5-72B-Instruct72BQwen (Alibaba) PerformancebenchmarkPerformancetest Small 1.0 | 2,28 tok/s TG Prefill 81 · TTFT 569 ms | 1× | NVIDIA Tesla V100 PCIe 32GB4x Intel(R) Xeon(R) CPU E5-4657L v2 @ 2.40GHz · 504 GB RAM | llama.cppgodclawQ4_K_M | Details → |