Skip to content
llmwise
Sign inStart free

Best AI · RAG and answering from documents

The best AI for RAG and answering from documents

In our test runs of September 27, 28, 29 and October 2, 7, 8, 9, 15, 2026, 20 of the 20 models passed 5 of 5 RAG and answering from documents prompts, so these prompts don't name one best model. For best value, GLM 5.3 (5 of 5). Our picks below follow fixed rules, beside each model's price per message, and every prompt and reply is published.

Start freeSee pricing

Based on 100 of our test runs on , through OpenRouter with the app's own prompt and settings. Updated .

Short answer

In our test runs on October 15, 2026, all 20 models passed 5 of 5 RAG and answering from documents prompts, so these prompts don't pick one for hard problems. For value, GLM 5.3 (5 of 5), 250 a month on Pro; for everyday RAG and answering from documents, GPT-6 Luna (5 of 5), from the daily count.

Our picks for RAG and answering from documents

  • Hard problems

    Shared by 20 models

    All 20 models passed 5 of 5, both hard ones: Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5 and 17 more. These prompts don't tell them apart, so they share the pick.

  • Best value

    GLM 5.3

    Passed 5 of 5 RAG and answering from documents prompts, with 250 a month on Pro.

  • Everyday

    GPT-6 Luna

    Passed 5 of 5 RAG and answering from documents prompts; an everyday model, so its messages come from the daily count (60 a day on Pro), not the monthly allowance.

These picks aren't our opinion: they're what the results below give, by these rules, among all 20 models in llmwise. They change when the results do.

  • Hard problems: the model that passed the most prompts and, of those, the most hard ones. Models level on both share the pick: the prompts don't tell them apart, so we don't break the tie by price or by name.
  • Best value: among the models that draw on the monthly allowance, the one with the most messages on Pro that passed no more than one prompt fewer than the top model. Ties go to the one that passed more, then to the lower cost per reply.
  • Everyday: among the cheapest models on the page (the everyday models, which come from the daily count, when the page has any), the one that passed the most. Ties go to the one that passed more of the hard prompts, then to the lower cost per reply.

Our RAG and answering from documents test runs, model by model

How each model did on our 5 RAG and answering from documents prompts, what each reply counted as on Pro, and what it cost to run.

Our RAG and answering from documents test runs
ModelPassedHard onesMessages used on ProCost per replyTime per reply
Claude Fable 5.1Anthropic5 of 52 of 21 each, of 31 a month on Pro$0.01454.9 s
Claude Opus 5.5Anthropic5 of 52 of 21 each, of 62 a month on Pro$0.00733.8 s
Claude Sonnet 5.5Anthropic5 of 52 of 21 each, of 125 a month on Pro$0.00281.3 s
Claude Sonnet 5Anthropic5 of 52 of 21 each, of 125 a month on Pro$0.00221.9 s
Claude Haiku 5.5Anthropic5 of 52 of 21 each, of 60 a day on Pro$0.00011.2 s
Claude Haiku 4.5Anthropic5 of 52 of 21 each, of 250 a month on Pro$0.00101.3 s
GPT-6 AstraOpenAI5 of 52 of 21 each, of 31 a month on Pro$0.00791.8 s
GPT-6.1 SolOpenAI5 of 52 of 21 each, of 125 a month on Pro$0.00081.5 s
GPT-6 SolOpenAI5 of 52 of 21 each, of 125 a month on Pro$0.00161.3 s
GPT-6 LunaOpenAI5 of 52 of 21 each, of 60 a day on Pro$0.00011.3 s
Gemini 4 ArgonGoogle5 of 52 of 21 each, of 62 a month on Pro$0.00123.6 s
Gemini 3.1 Pro (preview)Google5 of 52 of 21 each, of 125 a month on Pro$0.00586.2 s
Gemini 3.8 FlashGoogle5 of 52 of 21 each, of 250 a month on Pro$0.00073.2 s
DeepSeek V4.1 FlashDeepSeek5 of 52 of 21 each, of 60 a day on Pro$0.00020.5 s
DeepSeek V4 ProDeepSeek5 of 52 of 21 each, of 250 a month on Pro$0.00063.1 s
Grok 4.7xAI5 of 52 of 21 each, of 250 a month on Pro$0.00292.4 s
Kimi K3Moonshot5 of 52 of 21 each, of 125 a month on Pro$0.00153.2 s
GLM 5.3Z.ai5 of 52 of 21 each, of 250 a month on Pro$0.00050.8 s
GLM 5.3 FlashZ.ai5 of 52 of 21 each, of 60 a day on Pro$0.00022.3 s
Mistral Large 4Mistral5 of 52 of 21 each, of 250 a month on Pro$0.001411.1 s
Passed: out of the job's 5 prompts, how many replies passed their check (a reply the provider failed to give isn't counted). Messages used: what each reply counted as on Pro, and Pro's count on the model. Cost: what OpenRouter charged us per reply, on average; in llmwise you pay per message, not per token. Time: from sending to the whole reply.

One prompt, side by side

Each model's reply to “A later amendment changes the answer”, as it came, with whether it passed and what it cost.

The prompt: A later amendment changes the answer (hard)
Answer only from the handbook below, and cite the section you used, like (§3). If the handbook doesn't say, reply that it isn't in the handbook.

Harbor & Pine employee handbook (excerpt)

§1 Working hours. Core hours are 10:00 to 16:00. You can start any time between 07:30 and 10:00.
§2 Remote work. Staff can work remotely up to 3 days a week; interns 1 day a week. Requests to work fully remote go to the People team.
§3 Equipment. Laptops are replaced every 4 years. Monitors are available on request. New staff get a one-time home office stipend of €600 when they start.
§4 Parental leave. Every parent gets 16 weeks of leave at full pay. It can be split into two blocks, both taken within the child's first year.
§5 Holidays. Staff get 27 days a year plus public holidays. Up to 5 unused days carry over to the next year.
§6 Learning. Each person has €1,200 a year for courses and books. Unused learning budget doesn't carry over.
§7 Amendments (1 September 2026). For everyone who joins on or after 1 September 2026, the home office stipend in §3 is €900. Remote work for interns in §2 rises to 2 days a week.

Question: I'm an intern who started on 15 September 2026. How many days a week can I work remotely, and how big is my home office stipend?

  • Claude Fable 5.1

    Passed: Stated all 3 facts with the section.

    As an intern who joined on 15 September 2026 (on or after 1 September 2026), the amendments apply to you:

- **Remote work:** 2 days a week (§7, amending §2).
- **Home office stipend:** €900 one-time, since you're new staff starting after the amendment date (§7, amending §3).

    919 tokens in, 104 out · 7.1 s · $0.0165 · 1 message on Pro · answered by anthropic/claude-fable-5.1 via Anthropic ·

  • GLM 5.3

    Passed: Stated all 3 facts with the section.

    You can work remotely 2 days a week (§7), and your home office stipend is €900 (§7).

    704 tokens in, 60 out (33 of them reasoning) · 1.3 s · $0.0006 · 1 message on Pro · answered by z-ai/glm-5.3 via Wafer ·

  • GPT-6 Luna

    Passed: Stated all 3 facts with the section.

    You can work remotely up to 2 days a week, and your home office stipend is €900 (§2, §3, §7).

    659 tokens in, 33 out · 1.0 s · $0.0001 · 1 message on Pro · answered by openai/gpt-6-luna via OpenAI ·

The RAG and answering from documents prompts, and how they're scored

Key facts. Automatic. The answer must state each fact the handbook gives and cite its section, or say plainly that the handbook doesn't answer the question.

Each prompt was sent the way llmwise sends a message in a side-by-side comparison, which offers no tools: the app's own system prompt, the model's own settings, and Pro's reply size limit (8,000 tokens). Read all five RAG and answering from documents prompts and how every reply was scored.

Prompts like these to try yourself

What matters for RAG and answering from documents

  • Room for the documents

    The whole point is answering from your material, so the model must fit it: context windows are listed below.

  • Sticking to the sources

    A good model answers from the text you gave it, says when the answer isn't there, and doesn't fill gaps from memory.

  • Citations

    Quotes and page references let you check an answer in seconds.

Every model at a glance

Every model in llmwise
ModelOn ProOn FreeContext windowImagesPDFsReasoningAPI price per 1M, in / out
Claude Fable 5.1Anthropic31/mo on ProNo1M tokensYesWhole fileYes$10.00 / $50.00
Claude Opus 5.5Anthropic62/mo on ProNo1M tokensYesWhole fileYes$4.00 / $20.00
Claude Sonnet 5.5Anthropic125/mo on ProNo1M tokensYesWhole fileYes$2.00 / $10.00
Claude Sonnet 5Anthropic125/mo on ProNo1M tokensYesWhole fileYes$2.00 / $10.00
Claude Haiku 5.5Anthropic60/day on ProYes1M tokensYesWhole fileYes$0.10 / $0.50
Claude Haiku 4.5Anthropic250/mo on ProNo200K tokensYesWhole fileNo$1.00 / $5.00
GPT-6 AstraOpenAI31/mo on ProNo1.05M tokensYesWhole fileYes$10.00 / $50.00
GPT-6.1 SolOpenAI125/mo on ProNo1.05M tokensYesWhole fileYes$2.00 / $10.00
GPT-6 SolOpenAI125/mo on ProNo1.05M tokensYesWhole fileYes$2.00 / $10.00
GPT-6 LunaOpenAI60/day on ProNo1.05M tokensYesWhole fileYes$0.10 / $0.50
Gemini 4 ArgonGoogle62/mo on ProNo1.05M tokensYesWhole fileYes$4.00 / $20.00
Gemini 3.1 Pro (preview)Google125/mo on ProNo1.05M tokensYesWhole fileYes$2.00 / $12.00
Gemini 3.8 FlashGoogle250/mo on ProNo1.05M tokensYesWhole fileYes$0.75 / $3.75
DeepSeek V4.1 FlashDeepSeek60/day on ProNo1.05M tokensYesText onlyYes$0.30 / $1.20
DeepSeek V4 ProDeepSeek250/mo on ProNo1.05M tokensNoText onlyYes$0.40 / $4.00
Grok 4.7xAI250/mo on ProNo500K tokensYesWhole fileYes$2.00 / $6.00
Kimi K3Moonshot125/mo on ProNo1.05M tokensYesText onlyYes$3.00 / $15.00
GLM 5.3Z.ai250/mo on ProNo1.05M tokensNoText onlyYes$1.40 / $4.40
GLM 5.3 FlashZ.ai60/day on ProNo1.05M tokensYesText onlyYes$0.15 / $0.50
Mistral Large 4Mistral250/mo on ProNo1.05M tokensYesText onlyYes$0.68 / $2.09
Each badge is how many messages Pro gets on the model: a month’s, or a day’s on an everyday model. Free is a one-time trial of 5 messages on the models marked. “Text only” models get the text of a PDF, not the file. API prices are the per-token prices in our model catalog as of October 2026 (Anthropic: Anthropic's list price; OpenAI: OpenAI's list price; Google: Google's list price; DeepSeek: the price of the OpenRouter endpoints llmwise uses, not DeepSeek's own API; xAI: xAI's price, served through OpenRouter; Moonshot: Moonshot's list price; Z.ai: Z.ai's list price; Mistral: Mistral's price, served through OpenRouter). In llmwise you pay per message, not per token. Claude Haiku 5.5: the rate for prompts up to 100K tokens; $0.50 / $2.50 a million over that. Gemini 4 Argon: its standard price from December 1, 2026; $2 / $10 until then. Gemini 3.1 Pro (preview): the standard rate, for prompts up to 200K tokens. Gemini 3.8 Flash: an introductory price, through December 31, 2026. Grok 4.7: xAI charges more for very long prompts. Mistral Large 4: a sale price, half its list price of $1.36 / $4.18.

Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Plus $3.75, Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.

RAG and answering from documents in llmwise

  • Attach your documents

    Attach PDFs (up to 100 pages), images, Word, Excel, and PowerPoint files, and text or code files (plain text, Markdown, and CSV, JSON and more), up to 10 files a message.

  • Web search with sources

    The model can search the web and cite what it found as source cards, or read a link you paste. On Free, web search works inside your 5 trial messages; on a paid plan a search counts as one more message of the model in use.

  • Skills with reference files

    Put reference documents in a skill; the model reads the files it needs when a question calls for them.

  • Long chats, stated up front

    Past 64k tokens each reply counts as 2, past 128k as 4, and a chat stops at 200k; the composer says so before you send. One document set per chat keeps it short.

Tips

  • Ask the model to quote the passage each answer comes from.

  • Tell it to say so when the documents don't contain the answer.

  • Keep one set of documents per chat.

  • For a scanned PDF, use a model that takes the whole file: others only get the PDF's text.

Bar chart: Prompts passed in our test runs, rag and answering from documents. GPT-6 Luna: 5 of 5; Claude Haiku 5.5: 5 of 5; GLM 5.3 Flash: 5 of 5; DeepSeek V4.1 Flash: 5 of 5; GLM 5.3: 5 of 5; DeepSeek V4 Pro: 5 of 5; Gemini 3.8 Flash: 5 of 5; Claude Haiku 4.5: 5 of 5; Mistral Large 4: 5 of 5; Grok 4.7: 5 of 5; GPT-6.1 Sol: 5 of 5; Kimi K3: 5 of 5; GPT-6 Sol: 5 of 5; Claude Sonnet 5: 5 of 5; Claude Sonnet 5.5: 5 of 5; Gemini 3.1 Pro (preview): 5 of 5; Gemini 4 Argon: 5 of 5; Claude Opus 5.5: 5 of 5; GPT-6 Astra: 5 of 5; Claude Fable 5.1: 5 of 5.
Our test runs of September 27, 28, 29 and October 2, 7, 8, 9, 15, 2026: the same prompts for every model, each reply checked the same way.

Questions

What is the best AI for RAG and answering from documents?

In our test runs on October 15, 2026, 20 of the 20 models passed 5 of 5 RAG and answering from documents prompts, so these prompts don't name one best model. For best value, GLM 5.3 (5 of 5). For everyday, GPT-6 Luna (5 of 5). Every prompt and reply is published, so you can check them, and the picks follow fixed rules.

How did you test the models for RAG and answering from documents?

We sent the same RAG and answering from documents prompts to every model through llmwise's own pipeline and checked each reply the same way. The prompts, the replies, how each was scored and the grader are all published on the methods page.

Can I try these models for RAG and answering from documents for free?

Yes, to try: Free is a one-time trial of 5 messages on Claude Haiku 5.5.

Is attaching files the same as RAG?

Close to it. Retrieval-augmented generation means giving a model the relevant material at question time, so it answers from that rather than from memory. In llmwise you do that by attaching files, pasting links or letting the model search the web.

Can I build a RAG app on llmwise?

No. llmwise is a chat app with no API; building a RAG pipeline into your own product means calling a model provider's API from your code.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.

See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.

Start freeSee pricing