Evaluation Benchmarks
513 resources · page 10 of 17
OpenCompass HF leaderboard
by OpenCompass
OpenCompass LLM Leaderboard Hugging Face Space: OpenCompass evaluation results for language models.
OpenDriveLab Autonomous Grand Challenge 2025
by OpenDriveLab
OpenDriveLab Autonomous Grand Challenge 2025: CVPR 2025 autonomous-driving and embodied AI tracks such as NAVSIM.
OpenDriveLab events
by OpenDriveLab
OpenDriveLab events page listing its autonomous-driving and embodied AI challenges and workshops.
OpenML
by OpenML
OpenML: open platform for sharing machine-learning datasets, tasks, algorithms and experiment runs.
OpenRouter rankings
by OpenRouter
OpenRouter rankings: models ranked by tokens processed through the OpenRouter API, by app and category.
OSWorld 2.0
by XLANG Lab (University of Hong Kong)
OSWorld 2.0 site: benchmark of long-horizon real-world computer tasks for evaluating computer-use agents.
Polska AI przegrała z gigantami. Bielik i PLLuM wypadły słabo w testach (Bankier.pl)
by Bankier.pl
Bankier.pl article reporting a Polish LLM test of 20 tasks in which the Polish models Bielik and PLLuM were compared to global models.
P3D-Bench
by SpatiaOS
P3D-Bench GitHub repo: benchmark of MLLMs on parametric 3D generation and structural reasoning.
PDEBench
by pdebench
PDEBench GitHub repo: PDE datasets and baselines for scientific machine learning.
Phare
by Giskard
Giskard Phare site: multilingual benchmark of LLM safety and security, including hallucination, bias and harmful content.
PhysBench
by PhysBench
PhysBench project page: benchmark of physical-world questions testing vision-language models on objects, motion and interactions.
PhysioNet Challenges
by PhysioNet (MIT Laboratory for Computational Physiology)
PhysioNet Challenges page: annual open challenges on clinical physiological-signal analysis with scoring methods and data.
Polish LLM benchmarks (CodeSOTA)
by CodeSOTA
CodeSOTA page aggregating Polish LLM benchmark results for models such as Bielik, PLLuM, GPT, Claude and Gemini.
POPE
by Yifan Li
POPE GitHub repo (EMNLP 2023): polling-based evaluation of object hallucination in vision-language models.
PORTULAN Portuguese LLM Leaderboard
by PORTULAN
PORTULAN Portuguese LLM Leaderboard Hugging Face Space: live ranking of models on Portuguese tasks.
Procgen Benchmark
by OpenAI
OpenAI Procgen GitHub repo: procedurally generated game environments for RL generalisation.
ProgramBench
by ProgramBench
ProgramBench site: benchmark testing whether language models can rebuild complete programs from scratch.
ProteinGym
by Marks Lab (Harvard Medical School)
ProteinGym: benchmark and leaderboard for predicting the effects of protein mutations.
Pydantic AI
by Pydantic
Pydantic AI GitHub repo: type-safe Python agent framework with evals and durable execution.
Rapidata Image-to-3D
by Rapidata
benchmark.ai Image-to-3D leaderboard from Rapidata ranking 3D generation models by pairwise human preference votes.
RewardBench
by Ai2
RewardBench GitHub repo from Ai2: tool and dataset for evaluating reward models across preference categories.
RLBench
RLBench GitHub repo: large-scale benchmark and learning environment for robot manipulation.
RoboArena
by robo-arena
RoboArena: real-world evaluation of generalist robot policies through blind pairwise trials on DROID robots.
RoboCasa
by RoboCasa
RoboCasa site: large-scale kitchen simulation framework for training and evaluating household robot policies.
Robot learning leaderboard (RoboArena)
by RoboArena team (Pranav Atreya, Karl Pertsch et al.)
Robot-learning.ml leaderboard site for evaluating robot learning policies.
RoboTwin
RoboTwin 2.0 project page: dual-arm robot manipulation benchmark and simulated data generator.
RULER
NVIDIA RULER GitHub repo: synthetic benchmark measuring the real usable context length of long-context models.
Russian AI Alliance (Альянс в сфере ИИ)
Russian AI Alliance site, the industry association of Sber, Yandex, MTS and others that runs the MERA benchmark.
Russian SuperGLUE
by Natural Language Processing in Russian
Russian SuperGLUE GitHub repo: Russian general language understanding benchmark with tasks and baselines.
S-Eval
by IS2Lab
S-Eval GitHub repo: about 220,000 safety prompts, including adversarial variants, for automated LLM safety evaluation.
S-Eval leaderboard (Alibaba)
Alibaba S-Eval leaderboard in Chinese: safety evaluation rankings of large language models.
SafetyBench
by thu-coai
SafetyBench GitHub repo from Tsinghua: multiple-choice safety benchmark for LLMs across seven categories, in Chinese and English.