27 Benchmarks & Leaderboards AI tools
AI services in the Benchmarks & Leaderboards field. Click a name to see its description, pricing and alternatives.
Aider Leaderboard
Aider's polyglot coding leaderboard measuring LLM performance across languages
Read the guide →Free + paidAPEX-Agents
Measures whether frontier AI agents can execute real long-horizon tasks
Read the guide →Free + paidARC-AGI-2
Stress-tests efficiency and capability of state-of-the-art AI reasoning systems
Read the guide →Free + paidContext-Bench
A benchmark for agentic context engineering
Read the guide →Free + paidCORE-Bench Hard
Agent installs deps, runs published scientific code, and answers questions
Read the guide →Free + paidLive-SWE-agent
Can software engineering agents self-evolve on the fly? A living benchmark
Read the guide →Free + paidLMSYS Chatbot Arena
Human-preference LLM ranking via pairwise comparisons
Read the guide →Free + paidMCP Atlas
Evaluates how well language models handle real-world tool use through MCP
Read the guide →Free + paidOpenRouter Rankings
Model market share, use-case categories, and app rankings on OpenRouter
Read the guide →Free + paidOSWorld
Benchmarks multimodal agents on open-ended tasks in real computer environments
Read the guide →Free + paidRepo Bench
Measures large-context reasoning, edit precision, and instruction adherence
Read the guide →Free + paidSWE-bench
Evaluates LLM performance on real-world software issues collected from GitHub
Read the guide →Free + paidSWE-bench Multilingual
300 curated SWE-bench tasks from 42 repositories across 9 programming languages
Read the guide →Free + paidSWE-Bench Pro Public
Public version of Scale AI's SWE-Bench Pro for real-world software engineering
Read the guide →Free + paidSWE-DEV
Evaluating and training autonomous feature-driven software development agents
Read the guide →Free + paidSWE-rebench
Continuously evolving and decontaminated benchmark for software engineering LLMs
Read the guide →Free + paidVending-Bench 2
Measuring AI model performance on running a business over long time horizons
Read the guide →Free + paidτ-bench
Benchmarking AI agents in collaborative real-world scenarios
Read the guide →Free + paidBigCodeArena
A human-in-the-loop platform for evaluating code generation through execution
View on the 3D map →Free + paidLiveCodeBench
Holistic and contamination-free evaluation of large language models for code
View on the 3D map →Free + paidLiveCodeBench Pro
Codeforces, ICPC, and IOI problems; regularly updated to prevent contamination
View on the 3D map →Free + paidModu Merge Rate Leaderboard
Ranking top coding agents by real-world pull request merge success rates
View on the 3D map →Free + paidMulti-SWE-bench
Multilingual benchmark for issue resolving across multiple programming languages
View on the 3D map →Free + paidPR Arena
Software engineering agents head-to-head on real pull request tasks
View on the 3D map →Free + paidSWE-Bench Pro Commercial
Scale AI's real-world software engineering benchmark using a commercial dataset
View on the 3D map →Free + paidTerminal-Bench
Benchmark measuring AI agent capabilities in a terminal environment (v1)
View on the 3D map →Free + paidTerminal-Bench 2.0
Benchmark measuring AI agent capabilities in a terminal environment (v2)
View on the 3D map →