Benchmarks And Leaderboards: 512 curated resources

Curated material on benchmarks and leaderboards within evaluation.

512 resources · page 13 of 16

• VBench-2.0

  Creator not supplied; see original source.

  VBench-2.0 project page: video generation benchmark for intrinsic faithfulness, including physics and commonsense consistency.

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

• VBench Leaderboard (Hugging Face Space)

  Creator not supplied; see original source.

  VBench leaderboard Space: video generation model scores across VBench dimensions, with self-submission.

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

• VBench / VBench++ / VBench-2.0

  Creator not supplied; see original source.

  VBench GitHub repo: evaluation suite for video generation models across many quality and consistency dimensions.

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

• Vectara Hallucination Leaderboard (HHEM)

  Creator not supplied; see original source.

  Vectara hallucination leaderboard GitHub repo: hallucination rates of LLMs when summarising documents, scored with HHEM.

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

• Vellum LLM Leaderboard

  Creator not supplied; see original source.

  Vellum LLM leaderboard: compact comparison of models on benchmarks, speed and cost, with an open-source tab.

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

• MME-Benchmarks/Video-MME

  Creator not supplied; see original source.

  Video-MME GitHub repo: benchmark and evaluation resources for multimodal models' understanding of short to long videos.

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

• Video-MME

  Creator not supplied; see original source.

  Video-MME project site: benchmark for multimodal models on short, medium and long videos with subtitles and audio.

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

• Video-MME-v2

  Creator not supplied; see original source.

  Video-MME-v2 paper: a video-understanding benchmark with group-based consistency scoring for multimodal models.

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

• Vikhr Arena-Hard (RU) leaderboard

  Creator not supplied; see original source.

  Vikhr Arena-Hard Russian leaderboard Hugging Face Space: Russian-language Arena-Hard results for LLMs.

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

• VisualWebArena

  Creator not supplied; see original source.

  VisualWebArena project page: benchmark of realistic web tasks where multimodal agents need visual information to succeed.

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

• VLMEvalKit

  Creator not supplied; see original source.

  OpenCompass VLMEvalKit GitHub repo: evaluation toolkit for large vision-language models.

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

• VMLU

  Creator not supplied; see original source.

  VMLU site: Vietnamese multitask language-understanding benchmark suite for LLMs from ZaloAI and JAIST.

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

• VQA v2

  Creator not supplied; see original source.

  VQA site: Visual Question Answering datasets and challenges for answering open questions about images.

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

• W&B Weave

  Creator not supplied; see original source.

  W&B Weave GitHub repo: toolkit for tracing and evaluating AI applications.

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

• Waymo Open Dataset

  Creator not supplied; see original source.

  Waymo Open Dataset site: autonomous-driving perception and motion data with annual challenges.

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

• Waymo Open Dataset challenges

  Creator not supplied; see original source.

  Waymo Open Dataset challenges: autonomous-driving tasks and leaderboards on perception, prediction and planning.

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

• WeatherBench 2

  Creator not supplied; see original source.

  Google Research WeatherBench 2: benchmark, datasets and metrics for comparing data-driven global weather forecasting models.

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

• WebArena

  Creator not supplied; see original source.

  WebArena: suite of self-hosted website environments for benchmarking autonomous web agents.

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

• WILDS

  Creator not supplied; see original source.

  WILDS benchmark site from Stanford: real-world datasets with natural distribution shifts across domains such as medicine and ecology.

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

• Windows Agent Arena

  Creator not supplied; see original source.

  Windows Agent Arena GitHub repo from Microsoft: scalable Windows OS environment for testing multimodal computer-use agents.

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

• WorkArena

  Creator not supplied; see original source.

  ServiceNow WorkArena GitHub repo: benchmark of web agents on common enterprise knowledge-work tasks.

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

• WorldLens

  Creator not supplied; see original source.

  WorldLens GitHub repo (CVPR 2026): evaluations of driving world models across generation and reconstruction.

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

• WorldScore

  Creator not supplied; see original source.

  WorldScore project page: unified benchmark for 3D, 4D and video world generation on controllability, quality and dynamics.

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

• WorldScore Leaderboard (Hugging Face Space)

  Creator not supplied; see original source.

  WorldScore leaderboard Space: current model rankings on the WorldScore world-generation benchmark.

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

• ZeroBench

  Creator not supplied; see original source.

  ZeroBench project page: visual reasoning benchmark designed so current multimodal models score near zero.

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

• Zindi

  Creator not supplied; see original source.

  Zindi: competition platform hosting data-science and AI challenges with datasets and metrics, focused on Africa.

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

• ChinAI #315: Abandoned? Checking in on Three Key AI Safety Benchmarks

  Creator not supplied; see original source.

  ChinAI newsletter issue checking whether three Chinese AI safety benchmarks are still maintained.

  Beginner–Expert · unknown · unknown resource · en

• ChinAI #351: CAICT launches 2026 AI Safety Evaluations

  Creator not supplied; see original source.

  ChinAI newsletter issue 351 on CAICT's 2026 AI safety evaluations and lessons from its 2025 assessments.

  Beginner–Expert · unknown · unknown resource · en

• Your AI Product Needs Evals (Hamel Husain)

  Creator not supplied; see original source.

  Hamel Husain's essay on building domain-specific evaluation systems for LLM products.

  Beginner–Intermediate · unknown · unknown resource · en

• FLI AI Safety Index Summer 2026 (PDF)

  Creator not supplied; see original source.

  Future of Life Institute AI Safety Index Summer 2026 full report (PDF) with company grades by domain.

  Beginner–Expert · unknown · unknown resource · en

• What matters when evaluating AI agents for customer service (Intercom)

  Creator not supplied; see original source.

  Intercom post on criteria beyond performance for evaluating AI agents for customer service.

  Beginner · unknown · unknown resource · en

• Langfuse joins ClickHouse

  Creator not supplied; see original source.

  Langfuse post announcing the company joined ClickHouse and describing plans for the open-source project.

  Beginner · unknown · unknown resource · en

Plain-text Markdown copy