THE MODELS, SIDE BY SIDE
Which plan you need for each model, what it costs a month and what you get for free, plus how each one scores. Prices come from the labs' own pages: the US price first, the price in Austria under it.
THE SHORT ANSWER
- Free
- DeepSeek V4.1 Flash in the DeepSeek app · Kimi K3 in the Kimi app
- About $20 a month
- GPT-6.2 Astra with ChatGPT Plus ($20/month) · Claude Opus 5.5 with Claude Pro ($20/month) · Gemini 4 Neon with Google AI Pro ($19.99/month)
- From $100 a month
- Claude Fable 5.2 with Claude Max · Gemini 4 Carbon with Google AI Ultra
THE $20 TIER: IN OUR WEEKLY BLIND TEST
The best model each chat app gives you on its standard paid plan, about $20 a month, plus the two strongest free apps. These are the five models in the weekly blind test.
| Model | Plan you need | Price | Free in the app? | Epoch capability score | People's score |
|---|---|---|---|---|---|
| GPT-6.2 AstraOpenAI · ChatGPTEPOCH: TOP TIERLOWEST PRICE FOR ITS LEVEL | ChatGPT PlusIn Work and Codex, not regular chatChatGPT pricing | $20/month€23/month in Austria | No (Free gets a Luna model) | 172.8 (169.4–176.9) | Too few votes yet |
| Claude Opus 5.5Anthropic · ClaudeEPOCH #5 OF 258A SIMILAR MODEL IS FREE | Claude ProClaude pricing | $20/month, or $17/month billed yearlyfrom €15/month (billed yearly) in Austria | No (Free gets Sonnet) | 168.7 (165.9–172.0) | Too few votes yet |
| Gemini 4 NeonGoogle · Gemini | Google AI ProGoogle AI plans | $19.99/month€21.99/month in Austria | No | — | Too few votes yet |
| DeepSeek V4.1 FlashDeepSeek · DeepSeek · OPEN WEIGHTSEPOCH #24 OF 258FREE IN ITS APP | Free (Expert mode)DeepSeek chat | $0 | Yes | 159.4 (157.1–161.9) | Too few votes yet |
| Kimi K3Moonshot AI · Kimi · OPEN WEIGHTSEPOCH #26 OF 258FREE IN ITS APP | Free (Adagio)Kimi pricing | $0 | Yes, basic access | 158.6 (156.7–160.8) | Too few votes yet |
PREMIUM: PRICIER PLANS
Stronger or less limited models that need a more expensive plan. Not in the weekly blind test, which compares what a typical subscriber gets.
| Model | Plan you need | Price | Free in the app? | Epoch capability score |
|---|---|---|---|---|
| Claude Fable 5.2Anthropic · ClaudeEPOCH: TOP TIER5× THE PRICE OF SIMILAR MODELS | Claude MaxClaude pricing | $100/monthfrom €90/month in Austria | No | 173.4 (170.0–177.2) |
| Gemini 4 CarbonGoogle · GeminiEPOCH #3 OF 258A SIMILAR MODEL IS FREE | Google AI UltraGoogle AI plans | From $99.99/monthfrom €99.99/month (20× tier €219.99) in Austria | No | 169.7 (166.6–173.1) |
WHICH AI IS FOR ME?
Four taps. The answer comes from our blind-test votes, or the editor's pick until a task has enough votes.
See which AI wins each taskQuestion 1 of 4
Gemini 4 Neon
Gemini app · Google AI Pro, $19.99/month
Get it: Gemini app, or in your browser at gemini.google.com.
Use it in your browser at gemini.google.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for emailsAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Best regardless of price: Gemini 4 Neon (Gemini, $19.99/month).
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for emailsAlready paying for an AI? Check your setupClaude Opus 5.5
Claude app · Claude Pro, $20/month, or $17/month billed yearly
Get it: Claude apps, or in your browser at claude.ai.
Use it in your browser at claude.ai.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for codingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Best regardless of price: Claude Opus 5.5 (Claude, $20/month, or $17/month billed yearly).
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for codingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Good news: it's free, so there's no need to pay.
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for homework helpAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for homework helpAlready paying for an AI? Check your setupGemini 4 Neon
Gemini app · Google AI Pro, $19.99/month
Get it: Gemini app, or in your browser at gemini.google.com.
Use it in your browser at gemini.google.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for summarizingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Best regardless of price: Gemini 4 Neon (Gemini, $19.99/month).
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for summarizingAlready paying for an AI? Check your setupGemini 4 Neon
Gemini app · Google AI Pro, $19.99/month
Get it: Gemini app, or in your browser at gemini.google.com.
Use it in your browser at gemini.google.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for trip planningAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Best regardless of price: Gemini 4 Neon (Gemini, $19.99/month).
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for trip planningAlready paying for an AI? Check your setupGemini 4 Neon
Gemini app · Google AI Pro, $19.99/month
Get it: Gemini app, or in your browser at gemini.google.com.
Use it in your browser at gemini.google.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for recipesAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Best regardless of price: Gemini 4 Neon (Gemini, $19.99/month).
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for recipesAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Good news: it's free, so there's no need to pay.
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for spreadsheetsAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for spreadsheetsAlready paying for an AI? Check your setupGemini 4 Neon
Gemini app · Google AI Pro, $19.99/month
Get it: Gemini app, or in your browser at gemini.google.com.
Use it in your browser at gemini.google.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for brainstormingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Best regardless of price: Gemini 4 Neon (Gemini, $19.99/month).
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for brainstormingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Good news: it's free, so there's no need to pay.
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for translatingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for translatingAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Good news: it's free, so there's no need to pay.
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for adviceAlready paying for an AI? Check your setupKimi K3
Kimi app · Free (Adagio)
Get it: Kimi on the App Store, or in your browser at kimi.com.
Use it in your browser at kimi.com.
Our blind test is in English, so we can't yet say which AI is best in other languages.
The full ranking for adviceAlready paying for an AI? Check your setupCOST VS CAPABILITY
Higher means more capable on the Epoch Capabilities Index; further right costs more. Each line shows Epoch's 95% range: points whose lines overlap are about equally capable. Updated with every daily forecast.
Showing subscriptions: what you pay per month in each lab's chat app, with every model placed at the cheapest plan that unlocks it. Pricier tiers that only add usage (Kimi Plus, Pro and Max, ChatGPT Pro's higher tiers) aren't separate points.
Not shown: ChatGPT Business (the lab doesn't say which model version); Gemini Free (the lab doesn't say which model version); GPT-6.2 Sol (in ChatGPT Plus; Epoch hasn't scored it yet); Gemini 4 Neon (in Google AI Pro; Epoch hasn't scored it yet).
Chart data as a table
| Model | App | Cheapest way to get it | Epoch score (range) |
|---|---|---|---|
| Claude Fable 5.2 | Claude | $100/month with Claude Max | 173.4 (170.0–177.2) |
| GPT-6.2 Astra | ChatGPT | $20/month with ChatGPT Plus | 172.8 (169.4–176.9) |
| Gemini 4 Carbon | Gemini | $99.99/month with Google AI Ultra | 169.7 (166.6–173.1) |
| GPT-6 Astra | ChatGPT | $20/month with ChatGPT Plus | 169.2 (166.4–172.5) |
| Claude Opus 5.5 | Claude | $20/month with Claude Pro | 168.7 (165.9–172.0) |
| GPT-6.1 Sol | ChatGPT | $20/month with ChatGPT Plus | 168.6 (165.7–171.9) |
| GPT-6.1 Terra | ChatGPT | $100/month with ChatGPT Pro | 167.7 (164.9–171.0) |
| Gemini 4 Hydrogen | Gemini | $4.99/month with Google AI Plus | 166.8 (164.0–170.1) |
| Claude Sonnet 5.5 | Claude | free with Claude Free | 166.6 (163.9–169.6) |
| GPT-6 Sol | ChatGPT | $20/month with ChatGPT Plus | 163.8 (161.4–166.6) |
| GPT-5.6 Sol | ChatGPT | $20/month with ChatGPT Plus | 163.0 (160.7–165.6) |
| Kimi K3.1 Pro | Kimi | $39/month with Kimi Pro | 161.2 (158.9–163.7) |
| GPT-5.6 Terra | ChatGPT | $20/month with ChatGPT Plus | 160.8 (158.5–163.3) |
| Claude Haiku 5.5 | Claude | free with Claude Free | 160.3 (158.2–162.7) |
| DeepSeek V4.1 Flash 1017 | DeepSeek | free with DeepSeek Free (Expert mode) | 159.4 (157.1–161.9) |
| Kimi K3 | Kimi | free with Kimi Free (Adagio) | 158.6 (156.7–160.8) |
| GPT-5.6 Luna | ChatGPT | $20/month with ChatGPT Plus | 156.7 (154.9–158.8) |
| GPT-6 Luna | ChatGPT | free with ChatGPT Free | 156.4 (154.6–158.5) |
Showing API prices: what developers pay per million tokens on the lab's own servers. There's no free tier here.
62 models released in the last 12 months that their own lab serves on OpenRouter and Epoch scores. On a computer, hover over a point for its name; the table below lists them all. All recent models has the rest, including those no lab serves or Epoch hasn't scored.
Chart data as a table
| Model | Lab | API price | Epoch score (range) |
|---|---|---|---|
| Claude Fable 5.2 | Anthropic | $8 in / $40 out per million tokens | 173.4 (170.0–177.2) |
| GPT-6.2 Astra | OpenAI | $8 in / $40 out per million tokens | 172.8 (169.4–176.9) |
| Gemini 4 Carbon | $2 in / $10 out per million tokens | 169.7 (166.6–173.1) | |
| GPT-6 Astra | OpenAI | $10 in / $50 out per million tokens | 169.2 (166.4–172.5) |
| Claude Opus 5.5 | Anthropic | $4 in / $20 out per million tokens | 168.7 (165.9–172.0) |
| GPT-6.1 Sol | OpenAI | $2 in / $10 out per million tokens | 168.6 (165.7–171.9) |
| GPT-6.1 Terra | OpenAI | $1 in / $5 out per million tokens | 167.7 (164.9–171.0) |
| Claude Fable 5.1 | Anthropic | $10 in / $50 out per million tokens | 167.1 (164.4–170.1) |
| Gemini 4 Hydrogen | $1.50 in / $7.50 out per million tokens | 166.8 (164.0–170.1) | |
| Claude Sonnet 5.5 | Anthropic | $2 in / $10 out per million tokens | 166.6 (163.9–169.6) |
| Gemini 4 Argon | $2 in / $10 out per million tokens | 166.5 (163.9–169.5) | |
| Claude Opus 5 | Anthropic | $5 in / $25 out per million tokens | 164.7 (162.3–167.5) |
| Claude Fable 5 | Anthropic | $10 in / $50 out per million tokens | 164.2 (161.8–166.9) |
| GPT-6 Sol | OpenAI | $2 in / $10 out per million tokens | 163.8 (161.4–166.6) |
| GPT-5.6 Sol | OpenAI | $4 in / $20 out per million tokens | 163.0 (160.7–165.6) |
| GPT-5.5 Pro | OpenAI | $30 in / $180 out per million tokens | 162.8 (160.1–165.9) |
| Muse Wonder | Meta | $4 in / $20 out per million tokens | 161.7 (159.4–164.3) |
| Kimi K3.1 Pro | Moonshot AI | $2 in / $10 out per million tokens | 161.2 (158.9–163.7) |
| GPT-5.6 Terra | OpenAI | $2 in / $12 out per million tokens | 160.8 (158.5–163.3) |
| Claude Haiku 5.5 | Anthropic | $0.10 in / $0.50 out per million tokens | 160.3 (158.2–162.7) |
| GPT-5.4 Pro | OpenAI | $30 in / $180 out per million tokens | 160.3 (157.9–163.0) |
| GPT-5.5 | OpenAI | $5 in / $30 out per million tokens | 160.2 (158.2–162.4) |
| Claude Opus 4.8 | Anthropic | $5 in / $25 out per million tokens | 159.9 (157.8–162.2) |
| DeepSeek V4.1 Flash 1017 | DeepSeek | $0.15 in / $0.60 out per million tokens | 159.4 (157.1–161.9) |
| Gemini 3.8 Flash | $0.75 in / $3.75 out per million tokens | 158.8 (156.8–161.0) | |
| Kimi K3 | Moonshot AI | $3 in / $15 out per million tokens | 158.6 (156.7–160.8) |
| Gemini 3.7 Flash | $0.75 in / $3.75 out per million tokens | 158.4 (156.5–160.6) | |
| Muse Spark 1.3 | Meta | $1.25 in / $4.25 out per million tokens | 158.2 (156.2–160.5) |
| GPT-5.4 | OpenAI | $2.50 in / $15 out per million tokens | 157.9 (156.0–160.0) |
| Grok 4.6 | xAI | $2 in / $6 out per million tokens | 157.8 (155.9–160.0) |
| Claude Opus 4.7 | Anthropic | $5 in / $25 out per million tokens | 157.5 (155.6–159.6) |
| GPT-5.2 Pro | OpenAI | $21 in / $168 out per million tokens | 157.3 (155.1–159.9) |
| Claude Sonnet 5 | Anthropic | $2 in / $10 out per million tokens | 156.9 (154.9–159.1) |
| GPT-5.6 Luna | OpenAI | $0.20 in / $1.20 out per million tokens | 156.7 (154.9–158.8) |
| GPT-6 Luna | OpenAI | $0.10 in / $0.50 out per million tokens | 156.4 (154.6–158.5) |
| Grok 4.7 | xAI | $2 in / $6 out per million tokens | 156.4 (154.5–158.5) |
| Claude Opus 4.6 | Anthropic | $5 in / $25 out per million tokens | 156.3 (154.6–158.3) |
| Qwen3.8 Max (0902) | Alibaba | $2 in / $6 out per million tokens | 156.0 (153.9–158.3) |
| DeepSeek V4 Pro 0813 | DeepSeek | $0.66 in / $1.98 out per million tokens | 156.0 (154.1–158.1) |
| Gemini 3.5 Flash | $1.50 in / $9 out per million tokens | 155.3 (153.5–157.3) | |
| Gemini 3.6 Flash | $0.75 in / $3.75 out per million tokens | 155.2 (153.4–157.3) | |
| Muse Spark 1.2 | Meta | $1.25 in / $4.25 out per million tokens | 155.0 (152.7–157.5) |
| Grok 4.5 | xAI | $2 in / $6 out per million tokens | 155.0 (153.1–156.9) |
| Muse Spark 1.1 | Meta | $1.25 in / $4.25 out per million tokens | 154.9 (152.4–157.7) |
| Mistral Large 4 | Mistral | $0.70 in / $2.10 out per million tokens | 154.6 (151.8–157.4) |
| Qwen3.7-Max | Alibaba | $1.48 in / $4.42 out per million tokens | 154.6 (152.6–156.8) |
| GPT-5.2 | OpenAI | $1.75 in / $14 out per million tokens | 154.5 (152.9–156.3) |
| Claude Sonnet 4.6 | Anthropic | $3 in / $15 out per million tokens | 152.8 (151.2–154.5) |
| Grok 4.20 | xAI | $1.25 in / $2.50 out per million tokens | 152.3 (150.5–154.1) |
| Claude Opus 4.5 | Anthropic | $5 in / $25 out per million tokens | 151.9 (150.3–153.4) |
| Kimi K2.6 | Moonshot AI | $0.95 in / $4 out per million tokens | 151.6 (149.9–153.4) |
| Kimi K2.7 Code | Moonshot AI | $0.95 in / $4 out per million tokens | 151.2 (149.2–153.3) |
| GPT-5.4 Mini | OpenAI | $0.75 in / $4.50 out per million tokens | 149.4 (147.7–151.1) |
| Qwen3.5 397B-A17B | Alibaba | $0.39 in / $2.34 out per million tokens | 148.0 (145.9–150.1) |
| Qwen3.7-Plus | Alibaba | $0.32 in / $1.28 out per million tokens | 147.9 (146.0–150.0) |
| Qwen3.6 27B | Alibaba | $0.45 in / $2.70 out per million tokens | 146.7 (144.6–148.9) |
| GPT-5.4 Nano | OpenAI | $0.20 in / $1.25 out per million tokens | 146.4 (144.7–148.0) |
| Gemini 3.5 Flash-Lite | $0.30 in / $2.50 out per million tokens | 145.6 (144.0–147.2) | |
| Gemini 3.1 Flash-Lite | $0.25 in / $1.50 out per million tokens | 145.0 (142.8–147.1) | |
| Qwen3.5-35B-A3B | Alibaba | $0.16 in / $1.30 out per million tokens | 144.1 (141.5–146.6) |
| Mistral Medium 3.5 | Mistral | $1.50 in / $7.50 out per million tokens | 141.6 (138.3–144.7) |
| Gemma 4 26B A4B | $0.15 in / $0.60 out per million tokens | 141.6 (139.1–143.9) |
Sources: Epoch AI, Epoch Capabilities Index (CC BY 4.0); plan prices from the labs' pages (see Plans in detail); API prices from each lab's own servers via OpenRouter. Price isn't everything: plans differ in usage limits and features.
THE FRONTIER OVER TIME
Every model the Epoch Capabilities Index scores, placed at its release date. The step line is the best score so far: each step up is a model that took the lead when it came out. Labs leapfrog each other, so a model can lose the top spot within weeks.
New top scores in the last 12 months
- Mon 9 Nov 2026: Claude Fable 5.2 (Anthropic), 173.4
- Thu 3 Sept 2026: GPT-6 Astra (OpenAI), 169.2
- Tue 1 Sept 2026: Claude Fable 5.1 (Anthropic), 167.1
- Fri 24 Jul 2026: Claude Opus 5 (Anthropic), 164.7
- Tue 9 Jun 2026: Claude Fable 5 (Anthropic), 164.2
- Thu 23 Apr 2026: GPT-5.5 Pro (OpenAI), 162.8
- Thu 5 Mar 2026: GPT-5.4 Pro (OpenAI), 160.3
- Thu 11 Dec 2025: GPT-5.2 Pro (OpenAI), 157.3
- Tue 18 Nov 2025: Gemini 3 Pro (Google), 153.0
Source: Epoch AI, Epoch Capabilities Index (CC BY 4.0), updated with every daily forecast. Epoch averages public benchmarks; it doesn't measure everything a model is good at.
WHAT THE NUMBERS MEAN
- Plan you need: the cheapest plan that lets you pick the model in the lab's own chat app.
- Price: the lab's US price per month, before tax. Under it, the price shown in Austria, including VAT. Prices differ by country and can change without notice, so check the lab's page before you buy.
- Badges: "Epoch: top tier" means the model is level with Epoch's #1 within Epoch's uncertainty (one's score falls inside the other's range); otherwise "Epoch #" is its position among all 258 models the Epoch Capabilities Index scores. The price badge compares the plan price with every model in a chat plan of similar capability (the same ones as the cost vs capability chart), meaning one model's Epoch score falls inside the other's range: "Lowest price for its level" is within 10% of the cheapest similar model, and "A similar model is free" means one of them costs nothing.
- Epoch capability score: the Epoch Capabilities Index, which combines many public benchmarks into one scale (higher is better), with its range. Updated Tue 17 Nov. Epoch AI, CC BY 4.0.
- People's score: our weekly blind test, where people pick between two anonymous answers. 1000 is average; the range shows how sure we are. Preference, not a fact check. How we score
Spotted a mistake? Email corrections@dailyaiweather.com
FOR DEVELOPERS: API PRICES
If you build with these models instead of using the chat apps. Chat-app users don't pay these prices.
| Model | API price per million tokens, in / out | Our test: cost per answer |
|---|---|---|
| GPT-6.2 AstraOpenAI | $8 / $40 | — |
| Claude Opus 5.5Anthropic | $4 / $20 | 1.8¢ · 295 words on average |
| Gemini 4 NeonGoogle | $3 / $15 | — |
| DeepSeek V4.1 FlashDeepSeek | $0.15 / $0.60 | — |
| Kimi K3Moonshot AI | $3 / $15 | 2.0¢ · 210 words on average |
| Claude Fable 5.2Anthropic | $8 / $40 | — |
| Gemini 4 CarbonGoogle | $2 / $10 | — |
- API price: the lab's own standard price on its servers, via OpenRouter, per million tokens (about 750,000 words) going in and coming out. Updated daily.
- Cost per answer: what one blind-test answer actually cost us through the API, averaged over every prompt so far, with the average length.