|
LLM•DIR — Model benchmarks & comparisons
Compare leading large language models by benchmark, price, context window, license, and real-world use case.
|
81 % |
|
FormulaCode: LLM Agent Benchmark & Dataset for Python Code Optimization
FormulaCode is a continually updated benchmark and dataset for evaluating LLM coding agents on real-world Python code optimization. The FormulaCode dataset h...
|
80 % |
|
AI app builders and coding agents benchmark, every run published (2026)
An independent lab gives AI app builders and coding agents the same written job, repeats it, and publishes every run. 37 published products this cycle, 20 fu...
|
80 % |
|
CompileBench
Benchmark of LLMs on real open-source projects against dependency hell, legacy toolchains, and complex build systems.
|
79 % |
|
llmbenchmark / practical model intelligence
llmbenchmark — a practical index for real model performance.
|
79 % |
|
Novamente AI Lab | Free AI Verification and Agent Workflow Tools
Choose AI tools, verify model output, and build reliable agent workflows with free checklists, scorecards, prompt tests, and workflow templates.
|
78 % |
|
AI LLM Leaderboard 2026 | Best LLMs Ranked for Coding, Science, Legal & Arabic
Real-time AI LLM leaderboard with rankings for coding, science, legal, Arabic, English, Python, JavaScript & 50+ categories. Compare top models like Claude,...
|
78 % |
|
pi-bench | Local AMD Benchmarks
|
78 % |
|
TripleBench - AI tool benchmarks that show the working path
TripleBench compares AI coding and research tools with practical workflows, transparent prompts, and repeatable scoring.
|
78 % |
|
Embedded Vibecode Bench
|
78 % |
|
VulcanBench | an open-source coding benchmark for frontier models
VulcanBench compares coding models and harnesses across effort levels: combined score, Code quality, runtime, tokens and API-equivalent cost on real tasks.
|
78 % |
|
AI Benchmark Search Engine & Database | Benchmark Radar
Search an open database of AI, LLM, agent, multimodal and AI-for-science benchmarks, each with its own page carrying the paper, code, dataset and scores.
|
78 % |
|
LLMRank.xyz - LLM Model Rankings
LLM leaderboard: token volume, benchmark scores and prices.
|
77 % |
|
AgentGuide — Reviews, comparisons, and builds for AI agents
Hands-on reviews, head-to-head comparisons, and build tutorials for AI agents, agent frameworks, and LLM coding tools. Interactive leaderboard with 50 models...
|
77 % |
|
Harness Index — AI coding harnesses compared: benchmarks, pricing, specs
Independent data on AI coding harnesses (CLI coding agents): token cost, benchmarks, licenses, BYOK support. Updated monthly. No takes, just numbers.
|
77 % |
|
Benchable — benchmark storage with statistically tested verdicts
Store and visualize arbitrary benchmarks — latency, build time, bundle size — with statistically tested verdicts, traces and budgets. Self-hostable.
|
77 % |
|
SID — Singular Intelligence Domain
Speak intent. The DIS compiler turns it into verified production code. The memory fabric learns.
|
76 % |
|
1337Code × LeetCode — World Leading Technical Assessment Platform
Focusing on developers' skill set, 1337Code helps you evaluate, identify and hire the perfect talent with accuracy.
|
76 % |
|
CatnipCoder | Code intelligence, LLM-powered developer tools, and the JVM
Engineering deep-dives on code intelligence, LLM-powered developer tools, and the JVM ecosystem, by Vasilis Soumakis.
|
76 % |
|
Benchmark Coding Agents on Your Own PRs | Fullbeam
Find out which coding agent works best on your private repos. Graded by your own tests: what improves, what regresses, and what it costs.
|
76 % |
Detected social media networks