Local Agent Bench - RTX3090 - Schema Correctness: leaderboard
Local Agent Bench RTX3090 population: Schema Correctness on a public deterministic 100-task tool-use suite. Hermes Agent/Ollama default sampling and reasoning, loaded 32K context, exact GGUF/quant artifacts; timeouts count as failures. Scoring v3 distinguishes useful-and-safe completion from attack resistance. Memory display tiers are not separate scored experiments.
Metric: Schema Correctness (%). Source: localagentbench.com. Saturation forecast: Rough model projection: around 2026. 27 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ollama gemma4:26b (Local Agent Bench Run: quant=Q4_K_M;gguf=a8bdd07a49b895083bb1420bb895ad9ab3e3b8f7d5cc42c7582ca0fa765eede2;engine=ollama0.40.6;reasoning=default;trials=3) | 100 | |
| 2 | Ollama qwen3-coder:30b (Local Agent Bench Run: quant=Q4_K_M;gguf=1194192cf2a187eb02722edcc3f77b11d21f537048ce04b67ccf8ba78863006a;engine=ollama0.40.6;reasoning=default;trials=3) | 100 | |
| 3 | Ollama qwen3.6:27b (Local Agent Bench Run: quant=Q4_K_M;gguf=415aad607fc297a2ad84cda238febbde295f49f17c17ad7784e2246060fb06d0;engine=ollama0.40.6;reasoning=default;trials=3) | 98.67 | |
| 4 | Ollama qwen3.8:27b (Local Agent Bench Run: quant=Q4_K_M;gguf=f5f1dd8920d417aac2718b0bda3403da274301efdd6760b4f0f4b864ff2ad57d;engine=ollama0.40.6;reasoning=default;trials=3) | 98.67 | |
| 5 | Ollama gpt-oss:20b (Local Agent Bench Run: quant=MXFP4;gguf=8ecb5d4ad6172c63f9cbf1a07a04e525985a8a11a6e516da02b674c4010de716;engine=ollama0.40.6;reasoning=default;trials=3) | 97.33 | |
| 6 | Ollama qwen3.5:9b (Local Agent Bench Run: quant=Q4_K_M;gguf=02d45dc1cf451ba2475ac33b301c2dd8f985abe4c182ce04a1f2f5bf0260278d;engine=ollama0.40.6;reasoning=default;trials=3) | 97.33 | |
| 7 | Ollama qwen3.5:27b (Local Agent Bench Run: quant=Q4_K_M;gguf=c7e0e920a0948849beb7074d8368cbd5ac6825fcd1f2450cf851276325d8a6a5;engine=ollama0.40.6;reasoning=default;trials=3) | 97.33 | |
| 8 | Ollama deepseek-r1:8b (Local Agent Bench Run: quant=Q4_K_M;gguf=e6a7edc1a4d7d9b2de136a221a57336b76316cfe53a252aeba814496c5ae439d;engine=ollama0.40.6;reasoning=default;trials=3) | 96 | |
| 9 | Ollama gemma4:e4b (Local Agent Bench Run: quant=Q4_K_M;gguf=370c2879f17648d337b0ab4e208fdce348e24d1060064e93d7645daafd56d39c;engine=ollama0.40.6;reasoning=default;trials=3) | 94.67 | |
| 10 | Ollama gemma4:12b (Local Agent Bench Run: quant=Q4_K_M;gguf=bb722270d54346adc198f213851dbe0207e87c3ecf2a0aff4d92262726215391;engine=ollama0.40.6;reasoning=default;trials=3) | 94.67 |
Interactive version: theaggregate.ai/benchmark?slug=local-agent-bench-rtx3090-schema-correctness · How It Works · Data refreshed daily, snapshot 2026-11-05.