Navid MoazzezNavid Moazzez
AI consulting

AI model comparison

Compare 375 AI models by price and context window, and the top ones by intelligence, coding, agents and design, updated every week.

AI models compared
375
177 with an intelligence score
Highest intelligence score
57.6
Claude Opus 5.5 · Anthropic
Best score under $1
46.3
MiMo-V2.6-Pro · $0.54

AI model leaderboard

The top models on Artificial Analysis's indexes: intelligence across 10 evaluations, coding and agents. Prices are US dollars per million tokens, 3 parts input to 1 part output.

RankModel
1Claude Opus 5.5Anthropic57.6Lead$8
2Claude Sonnet 5.5Anthropic56.0#2$4
3Claude Fable 5.1Anthropic53.4#3$20
4GPT-6 AstraOpenAI52.7$20
5Gemini 4 ArgonGoogle52.6$4
6GPT-6.1 SolOpenAI51.8$4
7Claude Opus 5Anthropic50.8$10
8Claude Fable 5Anthropic49.6$20
9Muse Spark 1.3Meta48.1$2
10GPT-6 SolOpenAI47.6$4

Source: Artificial Analysis's indexes and OpenRouter's prices, in US dollars per million tokens, checked Oct 1, 2026

Data byArtificial AnalysisArtificial Analysis
See the full LLM leaderboard

What changed since Sept 30, 2026

Every sync compares each model with the one before: new models, prices that moved 5% or more, and scores that are new or moved half a point. Checked Oct 1, 2026.

New models

  • Gemini 4 ArgonGoogle · $4New
  • PPareto 26.10 Previewunbiased · $1.40New

Price changes

  • DeepSeek V4 Flash Latest$0.04 → $0.33+718%
  • DeepSeek V4 Pro 0423$0.98 → $0.26−73%
  • GLM Latest$1.10 → $0.38−66%
  • GLM 5.3$2.15 → $1.01−53%
  • Kimi K3$6 → $3.00−50%
  • DeepSeek Flash Latest$0.11 → $0.17+48%

New and moved scores

  • Solar Mini 4Intelligence 24.1New score
  • GPT-6 LunaIntelligence 38.1+0.8

Best score at every price

Each dot is a model. The line joins the models no cheaper model beats, so anything under it costs more for less.

Independent benchmark · Artificial Analysis

Intelligence against price, for every model with a score

Oct 1, 2026
Claude Opus 5.5 · $8Claude Sonnet 5.5 · $4Claude Fable 5.1 · $20Gemini 4 Argon · $4Claude Fable 5 · $20Muse Spark 1.3 · $2MiMo-V2.6-Pro · $0.54DeepSeek V4.1 Flash · $0.15Hy3 · $0.14

Source: Artificial Analysis's indexes and OpenRouter's prices, in US dollars per million tokens, checked Oct 1, 2026

Data byArtificial AnalysisArtificial Analysis

How to read this chart

Each dot is a model, placed by its price and its score. The models on the line are the value leaders: no cheaper model scores higher. Look toward the upper left for the best score for what you pay.

Comparison details

Prices are OpenRouter's list prices in US dollars per million tokens, blended 3 parts input to 1 part output, as Artificial Analysis does. Scores are Artificial Analysis's, checked Oct 1, 2026. Speed, latency and each provider's own price aren't part of the score.

Which AI designs best?

People vote blind between two designs made from the same prompt, and Design Arena turns the votes into a rating. Pick a category.

RankModel
1Muse Spark 1.3Meta1,364Lead59.2%$2
2Claude Opus 5.5Anthropic1,344#258.1%$8
3Kimi K3Open weightsMoonshot AI1,344#359.9%$3.00
4MiMo-V2.6-ProOpen weightsXiaomi1,32253.9%$0.54
5Claude Fable 5.1Anthropic1,32056.3%$20
6Muse Spark 1.2Meta1,31853.0%$2
7Claude Opus 5Anthropic1,31556.2%$10
8Gemini 3.7 FlashGoogle1,31155.6%$1.50
9GLM 5.3Open weightsZ.ai1,30855.0%$1.01
10Gemini 3.8 FlashGoogle1,30751.3%$1.50

Source: Design Arena's blind votes and OpenRouter's prices, checked Oct 1, 2026

See the full Best AI model for website design

Which AI makes the best images, video and voice?

People vote blind between two results of the same prompt on Artificial Analysis, and each model gets a rating with a 95% interval. Pick a board.

RankModel
1GPT Image 2.5 Sunburst (max)OpenAI1,197Lead±914,023
2GPT Image 2.5 Flare (max)OpenAI1,190#2±913,393
3GPT Image 2 (high)OpenAI1,172#3±915,346
4Grok Imagine Image 2.0SpaceXAI1,155±116,879
5MAI-Image-2.6Microsoft AI1,150±109,136
6Nano Banana 2 (Gemini 3.1 Flash Image)Google1,125±818,454
7Muse ImageMeta1,114±98,408
8GPT Image 1.5 (high)OpenAI1,107±814,933
9MAI-Image-2.6-FlashMicrosoft AI1,105±95,897
10MAI-Image-2.5Microsoft AI1,104±815,164

Source: Artificial Analysis's arenas, people's blind votes between two results of the same prompt, checked Oct 1, 2026

Data byArtificial AnalysisArtificial Analysis
See the full Best AI image model

Newest AI models

The latest models with a score, newest first.

Gemini 4 ArgonGoogle · Sept 30, 2026Intelligence 52.6 · $4
GPT-6.1 SolOpenAI · Sept 29, 2026Intelligence 51.8 · $4
Claude Sonnet 5.5Anthropic · Sept 28, 2026Intelligence 56.0 · $4
Solar Mini 4Upstage · Sept 23, 2026Intelligence 24.1 · $0.09
Claude Opus 5.5Anthropic · Sept 22, 2026Intelligence 57.6 · $8
Command A+Cohere · Sept 22, 2026Intelligence 13.1 · $0.60

Every leaderboard

Each board has its own page with every model, a chart and a CSV.

LLM leaderboard

Claude Opus 5.5 leads, from Anthropic

Best AI model for coding

Claude Fable 5.1 leads, from Anthropic

Best AI model for agents

Claude Fable 5.1 leads, from Anthropic

AI model pricing

Cheapest now: Mistral Nemo

Best AI model for writing

Best AI model for website design

Muse Spark 1.3 leads, from Meta

Best AI model for game development

Claude Opus 5.5 leads, from Anthropic

Best AI model for UI design

Claude Opus 5.5 leads, from Anthropic

Best AI model for data visualization

Claude Opus 5.5 leads, from Anthropic

Best AI model for SVG graphics

Claude Opus 5.5 leads, from Anthropic

Best AI model for 3D scenes

Claude Opus 5.5 leads, from Anthropic

Best AI model for building mobile apps

Claude Opus 5 leads, from Anthropic

Best AI model for building full-stack apps

Claude Fable 5.1 leads, from Anthropic

Best AI image model

GPT Image 2.5 Sunburst (max) leads, from OpenAI

Best AI image editing model

GPT Image 2.5 Sunburst (max) leads, from OpenAI

Best AI video model

Wan 3.0 leads, from Alibaba

Best image to video AI model

Gemini Omni Flash leads, from Google

Best AI voice model

Eleven v4 leads, from ElevenLabs

Where these numbers come from

Every model and price comes from OpenRouter's public model list, synced every week. The intelligence, coding and agentic scores are Artificial Analysis's, and the arena ratings are Design Arena's, both carried in that list. Last checked Oct 1, 2026.

  1. 01

    Collect

    Every week, the full model list comes from OpenRouter's public API: each model's maker, release date, context window and price per million tokens.

  2. 02

    Score

    Each model's scores come with it: Artificial Analysis's intelligence, coding and agentic indexes, and Design Arena's ratings from blind votes.

  3. 03

    Rank

    Each board ranks every model with a result on its measure, and prices blend 3 parts input to 1 part output, as Artificial Analysis does.

  4. 04

    Publish

    Every run is saved as a dated snapshot, and each board shows the day it was checked: Oct 1, 2026 for these.

How to read the numbers

Compare within a board

A score compares models on one measure. A 50 for intelligence and a 50 for coding don't mean the same thing.

Close scores are close

Neither source publishes error margins here, so treat models a point or two apart as close, not ranked.

Price sits beside the score

Scores measure quality only. The value chart puts each one next to what it costs.

What the scores don't cover

Speed and latency

How fast a model answers isn't part of any score here.

Other providers' prices

Prices are OpenRouter's list prices, and the maker or another provider may charge differently.

Your own work

No benchmark is your task, so test the top few models on your own prompts before you pick one.

How to cite these numbers

Name the page and the day it was checked:

Navid Moazzez, "AI model comparison," navid.me, updated Oct 1, 2026, https://navid.me/ai-models