🤖
Harness benchmark
How well does the model solve real tasks?
Quality on real agent and chat tasks – the model must handle real tasks with tools and multiple steps. Scored by success rate and task points achieved.
🎯 Success rate🏆 Task points🔧 Tool use🧠 real tasks
| # | Model / Maker | Metrics | GPU / CPU / RAM | Runtime | ||
|---|---|---|---|---|---|---|
| 1 | Kolibri-178.1BAleph Alpha Harness benchmarkOffice 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-AWQ35BQwen (Alibaba) Harness benchmarkDecision-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 | Qwen3.6-35B-A3B-AWQ35BQwen (Alibaba) Harness benchmarkDecision-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 → | |
| 4 | Open-Jev-27B-v1.127BZefan Cai / Open-Jev Harness benchmarkDecision-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 | pytorchpytorchBF16 | Details → | |
| 5 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-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 0.29.0FP8 | Details → | |
| 6 | Qwen3.6-35B-A3B-AWQ35BQwen (Alibaba) Harness benchmarkDecision-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 → | |
| 7 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-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 | vLLMdeterministic310 0.29.0FP8 | Details → | |
| 8 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-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 | vLLMdeterministic310 0.29.0NVFP4 | Details → | |
| 9 | Nemotron-Cascade-2-30B-A3B30BNVIDIA Harness benchmarkDecision-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 | vLLMvllmAWQ | Details → | |
| 10 | Laya0.4BConvai Innovations Harness benchmarkDecision-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 → | |
| 11 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-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 0.29.0FP8 | Details → | |
| 12 | Qwen3.6-35B-A3B-AWQ35BQwen (Alibaba) Harness benchmarkDecision-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 → | |
| 13 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-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 | vLLMdeterministic310 0.29.0NVFP4 | Details → | |
| 14 | Kolibri-178.1BAleph Alpha Harness benchmarkKolibri-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 | vLLMdeterministic310 0.29.0FP8 | Details → |