Reproducible, transparent AI model comparisons. Evidence over opinions. No sponsored rankings.https://losdoritos.com/en-ushttps://losdoritos.com/reports/mid-tier-llms-java-migration-scarfbench-benchmark/https://losdoritos.com/reports/mid-tier-llms-java-migration-scarfbench-benchmark/A report-driven benchmark proposal comparing Claude Sonnet 5, GPT-5.6 Terra/Sol, DeepSeek V4, and Gemini 3.5 Flash on ScarfBench-style Java migration tasks.Thu, 16 Jul 2026 00:00:00 GMThttps://losdoritos.com/benchmarks/python-bug-fix-async-handler/https://losdoritos.com/benchmarks/python-bug-fix-async-handler/Four frontier models attempt to fix a subtle async/await bug in a FastAPI endpoint. Evaluated on correctness, test pass rate, and minimal diff size.Thu, 12 Jun 2025 00:00:00 GMThttps://losdoritos.com/benchmarks/chart-data-extraction-vision/https://losdoritos.com/benchmarks/chart-data-extraction-vision/Vision-capable models extract structured data from a bar chart image. Scored on numerical accuracy and schema compliance.Sun, 08 Jun 2025 00:00:00 GMThttps://losdoritos.com/benchmarks/kubernetes-networking-writing/https://losdoritos.com/benchmarks/kubernetes-networking-writing/Models write a 1,200-word technical blog post explaining Kubernetes networking to intermediate developers. Evaluated on accuracy, structure, and clarity.Sun, 01 Jun 2025 00:00:00 GMThttps://losdoritos.com/methodology/updates/#scoring-rubric-v1/https://losdoritos.com/methodology/updates/#scoring-rubric-v1/How we score benchmarks: weighted criteria, human review protocols, and why we publish every rubric.Sun, 01 Jun 2025 00:00:00 GMThttps://losdoritos.com/benchmarks/river-crossing-reasoning/https://losdoritos.com/benchmarks/river-crossing-reasoning/Five models solve a classic reasoning puzzle with added constraints. Scored on logical validity, step completeness, and constraint satisfaction.Wed, 28 May 2025 00:00:00 GMThttps://losdoritos.com/methodology/updates/#prompt-standardization/https://losdoritos.com/methodology/updates/#prompt-standardization/How we standardize prompts across benchmarks to ensure fair, reproducible comparisons.Tue, 20 May 2025 00:00:00 GMThttps://losdoritos.com/benchmarks/climate-policy-research-synthesis/https://losdoritos.com/benchmarks/climate-policy-research-synthesis/Models synthesize findings from 8 provided research papers on carbon pricing. Scored on citation accuracy, synthesis quality, and hallucination rate.Thu, 15 May 2025 00:00:00 GMT