deepswe.datacurve.ai
DeepSWE
DeepSWE measures frontier coding agents on original, long-horizon software engineering tasks.
Visit deepswe.datacurve.ai ->
Only curated links
AI Coding Benchmark Directory
A handpicked collection of benchmark sites for comparing AI models, coding agents and real-world performance.
Benchmark
AI Models
llm-stats.com
Best AI for Coding 2026 - Top Coding Models
Compare the best AI for coding using live coding arena results, benchmark performance, and real generation examples for code generation, debugging, and software engineering.
Visit llm-stats.com ->
openrouter.ai
LLM Rankings | OpenRouter
LLM rankings and AI leaderboard by real-world usage, ranked by tokens processed through the OpenRouter API. See which AI models developers actually use.
Visit openrouter.ai ->
artificialanalysis.ai
Comparison of AI Models across Intelligence, Performance, and Price | Artificial Analysis
Comparison and analysis of AI models across key performance metrics including quality, price, output speed, latency, context window & others.
Visit artificialanalysis.ai ->
artificialanalysis.ai
AI Coding Agent Benchmarks & Leaderboard | Artificial Analysis
We measure real-world performance of coding agents on software engineering tasks, including cost, token usage, and execution time. We compare how performance changes across agents, models, and execution settings.
Visit artificialanalysis.ai ->
agi.safe.ai
Humanity's Last Exam
Humanity's Last Exam Dataset
Visit agi.safe.ai ->
vals.ai
AI Benchmarks and LLM Leaderboards | Vals AI
Vals AI evaluates models on the real tasks each industry relies on, with public leaderboards and benchmark methodology.
Visit vals.ai ->
labs.scale.com
AI Model Leaderboards & Benchmarks
Explore leaderboards with expert-driven LLM benchmarks and updated AI model rankings across coding, reasoning and more.
Visit labs.scale.com ->
labs.scale.com
SWE-Bench Pro
Compare the resolve rates of GPT-5.4, Muse Spark, Claude Opus 4.6, and Gemini 3.1 Pro on SWE-Bench Pro.
Visit labs.scale.com ->
lmcouncil.ai
AI Model Benchmarks | Compare GPT-5.6, Claude Fable 5 & Gemini 3 | LM Council
Compare GPT-5.6, Claude Fable 5, Claude Opus 5, Gemini 3, and other frontier models across Humanity's Last Exam, FrontierMath, GPQA, SWE-bench, and more. Every result snapshot links its source and checked date.
Visit lmcouncil.ai ->
petergpt.github.io
BullshitBench
Compare how AI models respond to nonsense: clear pushback, partial challenge, or accepting a broken premise.
Visit petergpt.github.io ->
arena.ai
Arena Leaderboard | Compare & Benchmark the Best Frontier AI Models
See how leading AI models stack up across text, image, vision, and more. This page provides a high-level snapshot of each Arena. Explore dedicated tabs for deeper insights.
Visit arena.ai ->
petribench.com
PetriBench
A benchmark for evaluating LLM reasoning over Petri nets.
Visit petribench.com ->
prarena.ai
PR Arena - AI Coding Agent Leaderboard
Explore benchmark and evaluation details from prarena.ai in a focused external resource.
Visit prarena.ai ->
10xbench.ai
10xBench — LLM Coding Benchmark in Astro, React, Tailwind & Cloudflare
See how leading LLMs perform when each gets a single shot at building a real production website in Astro, React, Tailwind and Cloudflare. Compare scores, screenshots and generated code side by side.
Visit 10xbench.ai ->
bridgebench.ai
Just a moment...
Explore benchmark and evaluation details from bridgebench.ai in a focused external resource.
Visit bridgebench.ai ->