general leaderboards: 248 curated resources
general leaderboards
248 resources · page 1 of 8
China's Most Powerful Large Model: Who Is the Real No.1 Among All Claimants? (36Kr)
by 36Kr
36Kr article comparing Chinese models across SuperCLUE, Artificial Analysis and Arena rankings.
AfroBench
Masakhane AfroBench collection on Hugging Face: datasets for benchmarking LLMs across many African languages.
AfroBench site/leaderboard
by McGill NLP
AfroBench site: benchmark evaluating LLMs on 64 African languages across 15 NLP tasks.
AGI-Eval (agi-eval.cn)
AGI-Eval: Chinese arena-style platform for evaluating large language models.
AI Fairness 360
by Trusted-AI
AIF360 GitHub repo (originally IBM): fairness metrics and bias mitigation algorithms for datasets and models.
AI4Bharat Launches Indic LLM Arena (CXO Digital Pulse)
CXO Digital Pulse report on AI4Bharat's Indic LLM Arena, a crowd-sourced evaluation platform for Indian languages.
AlignBench
by THUKEG
AlignBench GitHub repo: multi-dimensional benchmark for evaluating alignment of Chinese LLMs, with reference answers.
AlpaSim E2E Closed-Loop Challenge 2026
by OpenDriveLab
OpenDriveLab AlpaSim 2026 challenge: closed-loop benchmark for autonomous-driving policies on safety, generalisation and efficiency.
Apollo Research
Apollo Research site, an AI safety lab publishing evaluations of scheming and deceptive behaviour in frontier models.
ArabicMMLU
ArabicMMLU GitHub repo: Arabic knowledge benchmark built from school exams across North African, Levantine and Gulf regions.
Inception Multilingual Leaderboards
by Inception42
Inception multilingual leaderboards Hugging Face Space, including AraGen for Arabic generation.
ARC-AGI-3
ARC-AGI-3 page from ARC Prize: an interactive benchmark where agents must learn the rules of novel game environments.
Arcade Learning Environment
Documentation for the Arcade Learning Environment, the Atari 2600 interface used to train and evaluate reinforcement-learning agents.
Artificial Analysis
Artificial Analysis: independent benchmarks comparing AI models and API providers on intelligence, price, speed and latency.
Artificial Analysis large open-weight cohort
Artificial Analysis listing of open-weight models above 150B parameters with intelligence, speed and price measurements.
Artificial Analysis LLM leaderboard
Artificial Analysis LLM leaderboard comparing over 250 models on intelligence index, price, output speed and latency.
Artificial Analysis medium open-weight cohort
Artificial Analysis listing of open-weight models from 40B to 150B parameters with intelligence, speed and price measurements.
Artificial Analysis small open-weight cohort
Artificial Analysis listing of open-weight models from 4B to 40B parameters with intelligence, speed and price measurements.
Artificial Analysis tiny open-weight cohort
Artificial Analysis listing of open-weight models with 4B parameters or fewer, with intelligence, speed and price measurements.
AssistantBench
AssistantBench project page: realistic, time-consuming web tasks for evaluating whether web agents can complete them.
awesome-japanese-llm
by llm-jp
LLM-jp awesome-japanese-llm page: overview of public Japanese LLMs and Japanese evaluation benchmarks.
BEHAVIOR
by Stanford Vision and Learning Lab (BEHAVIOR)
BEHAVIOR project site from Stanford: a simulation benchmark of 1,000 everyday household activities for embodied AI agents.
BEHAVIOR Challenge (BEHAVIOR-1K)
by Stanford Vision and Learning Lab (BEHAVIOR)
BEHAVIOR Challenge page: a competition on full-length household tasks in the BEHAVIOR-1K simulator, with rules and results.
Bench2Drive
Thinklab-SJTU Bench2Drive GitHub repo (NeurIPS 2024): closed-loop benchmark for end-to-end autonomous driving.
BenchLM.ai
by BenchLM
BenchLM.ai: aggregator listing AI models across many benchmarks with scores, pricing and context windows.
BenCzechMark
BenCzechMark Hugging Face Space: Czech LLM benchmark leaderboard accepting model result submissions.
BHASA
by AI Singapore
BHASA GitHub repo from AI Singapore: linguistic and cultural evaluation suite for LLMs in Southeast Asian languages.
BIG-bench
by Google
BIG-bench GitHub repo from Google: collaborative benchmark of over 200 tasks probing language model capabilities.
BLEnD
BLEnD paper: a benchmark of everyday cultural knowledge questions across many countries and languages for evaluating LLMs.
BRIGHT
BRIGHT benchmark site: retrieval tasks that need reasoning beyond keyword or semantic matching, with leaderboard.
C-Eval
C-Eval GitHub repo: Chinese multi-subject evaluation suite for foundation models, with data and leaderboard.
CAC generative AI service filing count (Guangming Daily)
Guangming report (July 2026): CAC count of 988 generative AI services filed by 30 June.