General Leaderboards

248 resources · page 1 of 8

• China's Most Powerful Large Model: Who Is the Real No.1 Among All Claimants? (36Kr)

  Creator not supplied; see original source.

  36Kr article comparing Chinese models across SuperCLUE, Artificial Analysis and Arena rankings.

  Not applicable (entity) · unknown · unknown resource · en|zh

• AfroBench

  Creator not supplied; see original source.

  Masakhane AfroBench collection on Hugging Face: datasets for benchmarking LLMs across many African languages.

  Not applicable (entity) · unknown · unknown resource · en

• AfroBench site/leaderboard

  Creator not supplied; see original source.

  AfroBench site: benchmark evaluating LLMs on 64 African languages across 15 NLP tasks.

  Not applicable (entity) · unknown · unknown resource · mul

• AGI-Eval (agi-eval.cn)

  Creator not supplied; see original source.

  AGI-Eval: Chinese arena-style platform for evaluating large language models.

  Not applicable (entity) · unknown · unknown resource · zh

• AI Fairness 360

  Creator not supplied; see original source.

  AIF360 GitHub repo (originally IBM): fairness metrics and bias mitigation algorithms for datasets and models.

  Not applicable (entity) · unknown · unknown resource · en

• AI4Bharat Launches Indic LLM Arena (CXO Digital Pulse)

  Creator not supplied; see original source.

  CXO Digital Pulse report on AI4Bharat's Indic LLM Arena, a crowd-sourced evaluation platform for Indian languages.

  Not applicable (entity) · unknown · unknown resource · mul

• AlignBench

  Creator not supplied; see original source.

  AlignBench GitHub repo: multi-dimensional benchmark for evaluating alignment of Chinese LLMs, with reference answers.

  Not applicable (entity) · unknown · unknown resource · zh

• AlpaSim E2E Closed-Loop Challenge 2026

  Creator not supplied; see original source.

  OpenDriveLab AlpaSim 2026 challenge: closed-loop benchmark for autonomous-driving policies on safety, generalisation and efficiency.

  Not applicable (entity) · unknown · unknown resource · en

• Apollo Research

  Creator not supplied; see original source.

  Apollo Research site, an AI safety lab publishing evaluations of scheming and deceptive behaviour in frontier models.

  Not applicable (entity) · unknown · unknown resource · en

• ArabicMMLU

  Creator not supplied; see original source.

  ArabicMMLU GitHub repo: Arabic knowledge benchmark built from school exams across North African, Levantine and Gulf regions.

  Not applicable (entity) · unknown · unknown resource · ar

• Inception Multilingual Leaderboards

  Creator not supplied; see original source.

  Inception multilingual leaderboards Hugging Face Space, including AraGen for Arabic generation.

  Not applicable (entity) · unknown · unknown resource · ar

• ARC-AGI-3

  Creator not supplied; see original source.

  ARC-AGI-3 page from ARC Prize: an interactive benchmark where agents must learn the rules of novel game environments.

  Not applicable (entity) · unknown · unknown resource · mul

• Arcade Learning Environment

  Creator not supplied; see original source.

  Documentation for the Arcade Learning Environment, the Atari 2600 interface used to train and evaluate reinforcement-learning agents.

  Not applicable (entity) · unknown · unknown resource · en

• Artificial Analysis

  Creator not supplied; see original source.

  Artificial Analysis: independent benchmarks comparing AI models and API providers on intelligence, price, speed and latency.

  Not applicable (entity) · unknown · unknown resource · en

• Artificial Analysis large open-weight cohort

  Creator not supplied; see original source.

  Artificial Analysis listing of open-weight models above 150B parameters with intelligence, speed and price measurements.

  Not applicable (entity) · unknown · unknown resource · en

• Artificial Analysis LLM leaderboard

  Creator not supplied; see original source.

  Artificial Analysis LLM leaderboard comparing over 250 models on intelligence index, price, output speed and latency.

  Not applicable (entity) · unknown · unknown resource · en

• Artificial Analysis medium open-weight cohort

  Creator not supplied; see original source.

  Artificial Analysis listing of open-weight models from 40B to 150B parameters with intelligence, speed and price measurements.

  Not applicable (entity) · unknown · unknown resource · en

• Artificial Analysis small open-weight cohort

  Creator not supplied; see original source.

  Artificial Analysis listing of open-weight models from 4B to 40B parameters with intelligence, speed and price measurements.

  Not applicable (entity) · unknown · unknown resource · en

• Artificial Analysis tiny open-weight cohort

  Creator not supplied; see original source.

  Artificial Analysis listing of open-weight models with 4B parameters or fewer, with intelligence, speed and price measurements.

  Not applicable (entity) · unknown · unknown resource · en

• AssistantBench

  Creator not supplied; see original source.

  AssistantBench project page: realistic, time-consuming web tasks for evaluating whether web agents can complete them.

  Not applicable (entity) · unknown · unknown resource · en

• awesome-japanese-llm

  Creator not supplied; see original source.

  LLM-jp awesome-japanese-llm page: overview of public Japanese LLMs and Japanese evaluation benchmarks.

  Not applicable (entity) · unknown · unknown resource · ja

• BEHAVIOR

  Creator not supplied; see original source.

  BEHAVIOR project site from Stanford: a simulation benchmark of 1,000 everyday household activities for embodied AI agents.

  Not applicable (entity) · unknown · unknown resource · en

• BEHAVIOR Challenge (BEHAVIOR-1K)

  Creator not supplied; see original source.

  BEHAVIOR Challenge page: a competition on full-length household tasks in the BEHAVIOR-1K simulator, with rules and results.

  Not applicable (entity) · unknown · unknown resource · en

• Bench2Drive

  Creator not supplied; see original source.

  Thinklab-SJTU Bench2Drive GitHub repo (NeurIPS 2024): closed-loop benchmark for end-to-end autonomous driving.

  Not applicable (entity) · unknown · unknown resource · en

• BenchLM.ai

  Creator not supplied; see original source.

  BenchLM.ai: aggregator listing AI models across many benchmarks with scores, pricing and context windows.

  Not applicable (entity) · unknown · unknown resource · en

• BenCzechMark

  Creator not supplied; see original source.

  BenCzechMark Hugging Face Space: Czech LLM benchmark leaderboard accepting model result submissions.

  Not applicable (entity) · unknown · unknown resource · cs

• BHASA

  Creator not supplied; see original source.

  BHASA GitHub repo from AI Singapore: linguistic and cultural evaluation suite for LLMs in Southeast Asian languages.

  Not applicable (entity) · unknown · unknown resource · en

• BIG-bench

  Creator not supplied; see original source.

  BIG-bench GitHub repo from Google: collaborative benchmark of over 200 tasks probing language model capabilities.

  Not applicable (entity) · unknown · unknown resource · en

• BLEnD

  Creator not supplied; see original source.

  BLEnD paper: a benchmark of everyday cultural knowledge questions across many countries and languages for evaluating LLMs.

  Not applicable (entity) · unknown · unknown resource · mul

• BRIGHT

  Creator not supplied; see original source.

  BRIGHT benchmark site: retrieval tasks that need reasoning beyond keyword or semantic matching, with leaderboard.

  Not applicable (entity) · unknown · unknown resource · en

• C-Eval

  Creator not supplied; see original source.

  C-Eval GitHub repo: Chinese multi-subject evaluation suite for foundation models, with data and leaderboard.

  Not applicable (entity) · unknown · unknown resource · en

• CAC generative AI service filing count (Guangming Daily)

  Creator not supplied; see original source.

  Guangming report (July 2026): CAC count of 988 generative AI services filed by 30 June.

  Not applicable (entity) · unknown · unknown resource · zh

Plain-text Markdown copy