AI Listsby JustOut Today

AI Lists β€Ί AI Models & Benchmarks

AI Models & Benchmarks

Where to compare models: leaderboards, the benchmarks behind them, and each model family's official page.

🟒 Last checked Nov 20, 2026, 12:03 AM PT33 entries31 links verifiedDaily walkthrough · last run Nov 20, 2026, 12:03 AM PT

Rankings change weekly, so this list points to the live leaderboards and the official model pages rather than copying scores that go stale.

Leaderboards (6)

LMArena

Note: lmarena.ai now redirects here

Crowd-voted head-to-head model rankings.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Artificial Analysis

Independent comparisons of model quality, speed and price.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

LiveBench

Benchmark with fresh questions to limit contamination.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Aider LLM leaderboards

How well models edit code in Aider's polyglot benchmark.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

HELM

Stanford's holistic evaluation of language models.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

MTEB leaderboard

Massive Text Embedding Benchmark rankings.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Reasoning & knowledge benchmarks (9)

MMLU

57-subject multiple-choice knowledge test.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

GPQA

Graduate-level, 'Google-proof' science questions.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Humanity's Last Exam

Very hard expert-written questions across many fields.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

ARC-AGI

Abstract reasoning puzzles easy for people, hard for AI.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

FrontierMath

Unpublished research-level maths problems.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

MATH

Competition mathematics problems with step-by-step solutions.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

GSM8K

Grade-school maths word problems.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

MMMU

College-level multimodal understanding and reasoning.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

SimpleQA

Short factual questions to measure hallucination.

Site blocks bots Β· unverified New Source β†—

Coding & agent benchmarks (8)

SWE-bench

Can a model resolve real GitHub issues?

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

HumanEval

Classic Python function-writing benchmark.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Terminal-Bench

Agents completing real tasks in a terminal.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

tau-bench

Tool-using agents in customer-service style tasks.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

OSWorld

Agents operating real desktop computers.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

WebArena

Agents completing tasks on realistic websites.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

GAIA

General AI assistant tasks needing tools and browsing.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

BrowseComp

Hard-to-find facts that require persistent web browsing.

Site blocks bots Β· unverified New Source β†—

Model families (official pages) (8)

OpenAI models

Current OpenAI model list and capabilities.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Claude models

Current Claude model list.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Gemini models

Current Gemini API models.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Gemma

Google's open-weight model family.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Llama

Note: llama.com now redirects here

Meta's open-weight model family.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Mistral models

Mistral's open and commercial models.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Qwen

Alibaba's open model family on GitHub.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

DeepSeek

DeepSeek's open model releases on GitHub.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

Research trackers (2)

Epoch AI

Data on AI compute, models and trends.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

METR

Measures how long a task AI agents can finish on their own.

βœ“ Checked Nov 20, 2026, 12:03 AM PT New Source β†—

For AI agents and tools: JSON Β· Markdown Β· llms.txt Β· RSS. Page built Nov 20, 2026, 12:17 AM PT.