Topics
Results for “benchmarks”
55 results
- google/multimodal-knowledge-agent — Hugging Face Datasets · Seen
- google/physical-engineerings-last-exam — Hugging Face Datasets · Seen
- cais/hle — Hugging Face Datasets · Seen
- gaia-benchmark/GAIA — Hugging Face Datasets · Seen
- xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic — Hugging Face Models · Seen
- deepseek-ai/DeepSeek-V4.1-Flash-1017 — 2 sources · Seen
- Has GPT-6-Astra Achieved Embodied Intelligence? — Hugging Face Papers · Seen · 136 points
- High or Low Thinking? Gemini 4 and Gemma 4 on Hard Math, Cost First — DEV Community · Seen
- Benchmarks Don't Talk Back: Learning Through Self-Disagreement — arXiv AI Papers · Seen
- Unfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work Environments — arXiv AI Papers · Seen
- XYBench: Helping with the problem behind the question — Hugging Face Blog · Seen
- Six Serving Engines, One 8 GB GPU: Gemma 4 E2B on an RTX 3050 — DEV Community · Seen
- Beating benchmarks by weight-space optimizing decision models with DSPy — Hacker News · Seen · 8 points
- SynthCorp: A Platform for Creating Benchmarks for Data Agents — arXiv AI Papers · Seen
- Multimodal Graph Learning: A Survey of Models, Benchmarks, and Frontiers — arXiv AI Papers · Seen
- Brasilidade: Measuring Brazilian Identity for Large Language Models — arXiv AI Papers · Seen
- BIBIMBAP: A Benchmark for Instructional BIM-Based Automated Programming — arXiv AI Papers · Seen
- Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far — Hacker News · Seen · 370 points
- RikiyaT/Qwen3.5-0.8B-weight-space-programming — Hugging Face Models · Seen
- What Are LLM Agents Actually Learning on Low-Budget Molecular Optimization Benchmarks? — arXiv AI Papers · Seen
- MaxxBench – "Nice DeepSWE score. But is it true?" — Hacker News · Seen · 405 points
- A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks. — Hugging Face Blog · Seen
- I Retested My MoE Offloading Benchmarks. Some of My Conclusions Changed. — DEV Community · Seen
- Follow the Policy, Fail the Benchmark: Auditing and Revising Policy-Based Decision Benchmarks — arXiv AI Papers · Seen
- Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future? — Hugging Face Papers · Seen · 15 points
- CWE-bench v2: More coverage, quality, and transparency — Hugging Face Blog · Seen
- Zhanli-Li/DataWorld-Bench — Hugging Face Datasets · Seen
- Zhanli-Li/DataWorld-Train-2k-part2 — Hugging Face Datasets · Seen
- InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants — Hugging Face Papers · Seen · 46 points
- CohereLabsCommunity/CulturalRiddles — Hugging Face Datasets · Seen
- Show HN: ClickBench inspired leaderboard for multiple database benchmarks — Hacker News · Seen · 3 points
- llamaindex/ParseBench — Hugging Face Datasets · Seen
- Artificial Analysis v5 and the benchmarker's dilemma — Hacker News · Seen · 72 points
- tencent/Hy-Nomas-Bench — Hugging Face Datasets · Seen
- Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5 — Hacker News · Seen · 336 points
- Is GitHub Actions suitable for running benchmarks? — Lobsters · Seen · 13 points
- Benchmarks Are Surprisingly Compaction-Friendly — arXiv AI Papers · Seen
- Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox — Hugging Face Blog · Seen
- Debunking "Faster than Rust": Malicious Benchmarks in Tov — Lobsters · Seen · 46 points
- nyu-mll/glue — Hugging Face Datasets · Seen
- MathLLMs/MathVision — Hugging Face Datasets · Seen
- Remove pgrust: the entry is cheating — Hacker News · Seen · 190 points
- FusionEval: Benchmarking Model Fusion for Large Language Models — arXiv AI Papers · Seen
- Kimi K3.1 Pro puts open-source AI a month behind the best — Hacker News · Seen · 3 points
- Kimi K3.1 scores 55 on Artificial Analysis, placed on the Pareto line — Hacker News · Seen · 110 points
- prometheus-eval/into-the-unknown — Hugging Face Datasets · Seen
- BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References — Hugging Face Papers · Seen · 22 points
- GardenBench: A lightweight, daily evaluation of LLM capabilities — arXiv AI Papers · Seen
- I built a programming language that LLMs can't use — Hacker News · Seen · 275 points
- BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business — Hugging Face Papers · Seen · 341 points
- TIGER-Lab/MMLU-Pro — Hugging Face Datasets · Seen
- Ultramarine 1 Flash — Hacker News · Seen · 379 points
- Georgian Language Benchmark: Two Biggest AI Labs Clash in a Language That Doesn't Play by Anyone's Rules — DEV Community · Seen
- 90% of US working hours are spent on tasks not covered well by AI benchmarks — Hacker News · Seen · 612 points
- FrontierML: A challenging, end-to-end machine learning benchmark — Hacker News · Seen · 5 points