Benchmarks and news on various repros of TypeSafe's Jev

We asked the world's most advanced AI models to reason about human rights. They failed — scoring 51 to 58 percent, near chance.

Odysseys is a benchmark of 200 long-horizon web agent tasks, evaluated with rubric-based scoring on the live internet.

Compare AI models on real coding tasks with private benchmarks, live HTML previews, cost tracking, ELO battles, and public model rankings.

A benchmark built to evaluate and improve agent capabilities for supporting legal work. - harveyai/harvey-labs

Covers 183+ providers and 2100+ LLMs: pricing and capabilities, the same model compared across hosts for the lowest price, plus quality leaderboards and a free cost calculator.

The only AI benchmark that measures AGI progress.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Compare LLM API pricing for every major AI model in 2026. Side-by-side input/output token costs, price-to-performance scores, and cost calculators for GPT-5, Claude 4, Gemini 3, DeepSeek, Llama 4, and 100+ more.

Humanity's Last Exam Dataset

Compare 123 ranked models and 258 tracked AI models across 247 benchmarks with BenchLM scoring, pricing, context window, and runtime tradeoffs. Rankings and head-to-head comparisons for GPT-5, Claude, Gemini, DeepSeek, Llama, and more.

Explore DeepSWE benchmark results comparing GPT and Claude on long-horizon software engineering tasks, and see what they mean for AI coding users.

130+ real-world coding tasks. 6 categories. The benchmark built for vibe coding and agentic AI builders.

Chat with multiple AI models side-by-side. Compare ChatGPT, Claude, Gemini, and other top LLMs. Crowdsourced benchmarks and leaderboards.

Compare LLM API pricing across 300+ AI models. Updated daily with costs from OpenAI, Anthropic, Google, Meta, and more.

Compare large language models side by side. Updated rankings based on benchmarks, pricing, and real-world performance.

Explore AI model leaderboards to benchmark and compare the best frontier AI models across text, image, video, search, and code—ranked by human votes.

LLM rankings and leaderboard based on real usage data from millions of users. See which AI models developers actually use.

Browse 51545 open-source large and small language models conveniently grouped into various categories and llm lists complete with benchmarks and analytics.

Access the latest LLM leaderboard with comprehensive performance metrics and benchmark data. Compare top language models with interactive analysis tools.

List of spaces using ZERO-GPU Also in https://huggingface.co/spaces