🤖
Harness-Benchmark
Wie gut löst das Modell echte Aufgaben?
Qualität in echten Agenten- und Chat-Aufgaben – das Modell muss reale Aufgaben mit Tools und mehreren Schritten bearbeiten. Bewertet nach Erfolgsquote und erreichten Aufgabenpunkten.
🎯 Erfolgsquote🏆 Aufgabenpunkte🔧 Tool-Nutzung🧠 echte Aufgaben
| # | Modell / Hersteller | Messwerte | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|
| 1 | Kolibri-178.1BAleph Alpha HarnessbenchmarkOffice Agentic Work 100 - Tool Usage V1 | 100 Pkt 100,0% · 100/100 Aufg. · 547,7 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | officeagentic100NVFP4 | Details → | |
| 2 | Qwen3.6-35B-A3B-AWQ35.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark V 1.0 | 200 Pkt 100,0% · 200/200 Aufg. · 57,0 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMBuzzwordTrainAWQ | Details → | |
| 3 | Jev-1.13.0TypeSafe AI HarnessbenchmarkDecision-Benchmark V 1.0 | 200 Pkt 100,0% · 200/200 Aufg. · 51,8 s | Cloud/API: TypeSafe AI (Hardware unbekannt) i | apipython | Details → | |
| 4 | Qwen3.6-35B-A3B-AWQ35.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark V 1.0 | 200 Pkt 100,0% · 200/200 Aufg. · 36,2 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMvllmAWQ | Details → | |
| 5 | Qwen3.8-27B-Uncensored27.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark V 1.0 | 200 Pkt 100,0% · 200/200 Aufg. · 29,9 s | 2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMvllm | Details → | |
| 6 | Open-Jev-27B-v1.127.00BZefan Cai / Open-Jev HarnessbenchmarkDecision-Benchmark V 1.0 | 200 Pkt 100,0% · 200/200 Aufg. · 75,5 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | pytorchpytorch | Details → | |
| 7 | Kolibri-178.1BAleph Alpha HarnessbenchmarkKolibri-Qwen Diverse Deterministic 210 V1.0 | 207 Pkt 98,6% · 207/210 Aufg. · 1.080,2 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic210 | Details → | |
| 8 | Qwen3.6-35B-A3B-AWQ35.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark High V 1.0 | 193 Pkt 96,5% · 193/200 Aufg. · 3.667,6 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMvllmAWQ | Details → | |
| 9 | Kolibri-178.1BAleph Alpha HarnessbenchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 289 Pkt 93,2% · 289/310 Aufg. · 2.504,7 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310FP8 | Details → | |
| 10 | Kolibri-178.1BAleph Alpha HarnessbenchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 283 Pkt 91,3% · 283/310 Aufg. · 2.384,4 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310NVFP4 | Details → | |
| 11 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkTool Usage Standard 1.0 | 2.701 Pkt 90,6% · 16/16 Aufg. · 118,0 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | openclaw_cli | Details → | |
| 12 | Devstral-Small-2-24B-Instruct-251224BMistral AI HarnessbenchmarkTool Usage Standard 1.0 | 2.597 Pkt 87,1% · 16/16 Aufg. · 165,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 13 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkTool Usage Standard 1.0 | 2.440 Pkt 81,9% · 16/16 Aufg. · 218,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 123 GB RAM | openclaw_cli | Details → | |
| 14 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage Standard 1.0 | 2.427 Pkt 81,4% · 16/16 Aufg. · 228,0 s | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMgodclawBF16 | Details → | |
| 15 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkTool Usage Standard 1.0 | 2.383 Pkt 80,0% · 16/16 Aufg. · 245,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 123 GB RAM | openclaw_cli | Details → | |
| 16 | Nemotron-Cascade-2-30B-A3B30BNVIDIA HarnessbenchmarkDecision-Benchmark V 1.0 | 159 Pkt 79,5% · 159/200 Aufg. · 21,0 s | NVIDIA GeForce RTX 3090 iAMD Ryzen 5 5600X 6-Core Processor · 31 GB RAM | vLLMvllm | Details → | |
| 17 | Nemotron-Cascade-2-30B-A3B30BNVIDIA HarnessbenchmarkDecision-Benchmark V 1.0 | 159 Pkt 79,5% · 159/200 Aufg. · 35,0 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMvllm | Details → | |
| 18 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage Standard 1.0 | 2.340 Pkt 78,5% · 16/16 Aufg. · 266,0 s | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | openclaw_cli | Details → | |
| 19 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkTool Usage Standard 1.0 | 2.268 Pkt 76,1% · 16/16 Aufg. · 347,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 20 | Devstral-Small-2-24B-Instruct-251224BMistral AI HarnessbenchmarkGodBrain MCP Deep 40 - Wissensbasis-Lebenszyklus 1.0 | 5.738 Pkt 75,7% · 40/40 Aufg. · 1.879,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 21 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkTool Usage Standard 1.0 | 2.197 Pkt 73,7% · 16/16 Aufg. · 375,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | openclaw_cli | Details → | |
| 22 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage V 1.0 | 1.245 Pkt 70,7% · 15/15 Aufg. · 301,0 s | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | openclaw_cli | Details → | |
| 23 | Devstral-Small-2-24B-Instruct-251224BMistral AI HarnessbenchmarkTool Usage Extrem 40 - Tech-Radar Mission 1.0 | 5.629 Pkt 68,6% · 40/40 Aufg. · 2.018,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 24 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage Standard 1.0 | 2.033 Pkt 68,2% · 16/16 Aufg. · 373,0 s | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMgodclawBF16 | Details → | |
| 25 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTools Usage Mini 1.0 | 130 Pkt 65,0% · 2/2 Aufg. · 70,0 s | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | godclaw | Details → | |
| 26 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage V 1.0 | 1.079 Pkt 61,3% · 15/15 Aufg. · 457,0 s | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 63 GB RAM | openclaw_cli | Details → | |
| 27 | MiniMax-M2.7230BMiniMax HarnessbenchmarkTool-Parcours Dossier 40 V1.0 | 3.641 Pkt 61,1% · 40/40 Aufg. · 8.209,0 s | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | vLLMgodclawAWQ | Details → | |
| 28 | LayaConvai Innovations HarnessbenchmarkDecision-Benchmark V 1.0 | 122 Pkt 61,0% · 122/200 Aufg. · 14,1 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | pytorchpytorch | Details → | |
| 29 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool-Parcours Dossier 40 V1.0 | 3.622 Pkt 60,8% · 34/40 Aufg. · 7.862,0 s | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMgodclawBF16 | Details → | |
| 30 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage Standard 1.0 | 1.762 Pkt 59,1% · 16/16 Aufg. · 526,0 s | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | openclaw_cli | Details → | |
| 31 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTool Usage Standard 1.0 | 1.714 Pkt 57,5% · 16/16 Aufg. · 487,0 s | 3x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMgodclawBF16 | Details → | |
| 32 | Jev-1.13.0TypeSafe AI HarnessbenchmarkDecision-Benchmark High V 1.0 | 114 Pkt 57,0% · 114/200 Aufg. · 51,2 s | Cloud/API: TypeSafe AI (Hardware unbekannt) i | apipython | Details → | |
| 33 | Qwen3.8-27B-Uncensored27.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark High V 1.0 | 110 Pkt 55,0% · 110/200 Aufg. · 28,7 s | 2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMvllm | Details → | |
| 34 | Qwen3.8-Flash-Next-Uncensored-NVFP4180BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark High V 1.0 | 107 Pkt 53,5% · 107/200 Aufg. · 38,9 s | 2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMvllmNVFP4 | Details → | |
| 35 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTools Usage Mini 1.0 | 106 Pkt 53,0% · 2/2 Aufg. · 71,0 s | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 63 GB RAM | openclaw_cli | Details → | |
| 36 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTextgenerierung V 1.0 | 790 Pkt 52,0% · 15/15 Aufg. · 261,0 s | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | openclaw_cli | Details → | |
| 37 | Kolibri-178.1BAleph Alpha HarnessbenchmarkKolibri-Qwen Diverse Deterministic 210 V1.0 | 108 Pkt 51,4% · 108/210 Aufg. · 72,1 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic210 | Details → | |
| 38 | Qwen3.8-27B-Uncensored27.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark High V 1.0 | 101 Pkt 50,5% · 101/200 Aufg. · 36,8 s | 2x NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen Threadripper PRO 9965WX 24-Cores · 125 GB RAM | vLLMvllm | Details → | |
| 39 | Qwen3.6-35B-A3B-AWQ35.00BQwen (Alibaba) HarnessbenchmarkDecision-Benchmark High V 1.0 | 87 Pkt 43,5% · 87/200 Aufg. · 19,0 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition iAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMvllmAWQ | Details → | |
| 40 | Qwen3.6-27B27BQwen (Alibaba) HarnessbenchmarkTool Usage Standard 1.0 | 1.220 Pkt 40,9% · 16/16 Aufg. · 1.036,0 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 41 | Kolibri-178.1BAleph Alpha HarnessbenchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 119 Pkt 38,4% · 119/310 Aufg. · 87,9 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310NVFP4 | Details → | |
| 42 | Qwen3.6-27B27BQwen (Alibaba) HarnessbenchmarkTool-Parcours Dossier 40 V1.0 | 2.267 Pkt 38,0% · 38/40 Aufg. · 10.331,0 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 9950X 16-Core Processor · 92 GB RAM | vLLMgodclaw | Details → | |
| 43 | Kolibri-178.1BAleph Alpha HarnessbenchmarkKolibri-Qwen Diverse Deterministic 310 V2.0 | 115 Pkt 37,1% · 115/310 Aufg. · 99,6 s | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation EditionAMD Ryzen 9 7945HX with Radeon Graphics · 60 GB RAM | vLLMdeterministic310FP8 | Details → | |
| 44 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkGodBrain MCP Deep 40 - Wissensbasis-Lebenszyklus 1.0 | 2.271 Pkt 30,0% · 18/40 Aufg. · 982,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 45 | MiniMax-M2.7230BMiniMax HarnessbenchmarkTool Usage Standard 1.0 | 858 Pkt 28,8% · 16/16 Aufg. · 1.222,0 s | NVIDIA GB10 (DGX Spark)NVIDIA Grace · 120 GB RAM | godclaw | Details → | |
| 46 | Gemma-4-26B-A4B-it26BGoogle HarnessbenchmarkTool-Parcours Dossier 40 V1.0 | 1.489 Pkt 25,0% · 22/40 Aufg. · 8.783,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 47 | Devstral-Small-2-24B-Instruct-251224BMistral AI HarnessbenchmarkTool-Parcours Dossier 40 V1.0 | 1.436 Pkt 24,1% · 21/40 Aufg. · 8.887,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | llama.cppgodclawQ8_0 | Details → | |
| 48 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) HarnessbenchmarkTool Usage V 1.0 | 235 Pkt 13,4% · 15/15 Aufg. · 1.783,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 31 GB RAM | openclaw_cli | Details → | |
| 49 | gemma-4-31B-it31BGoogle HarnessbenchmarkTool Usage Standard 1.0 | 298 Pkt 10,0% · 16/16 Aufg. · 9.625,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 123 GB RAM | openclaw_cli | Details → | |
| 50 | Qwen2.5-32B-Instruct-AWQ32BQwen (Alibaba) HarnessbenchmarkTool Usage Standard 1.0 | 298 Pkt 10,0% · 16/16 Aufg. · 4.687,0 s | AMD Radeon 8060S GraphicsAMD RYZEN AI MAX+ 395 w/ Radeon 8060S · 123 GB RAM | openclaw_cli | Details → | |
| 51 | MiniMax-M2.5230BMiniMax HarnessbenchmarkTools Usage Mini 1.0 | 10 Pkt 10,0% · 1/1 Aufg. · 65,0 s | NVIDIA GeForce RTX 5090AMD Ryzen 7 5800X3D 8-Core Processor · 63 GB RAM | openclaw_cli | Details → |