1stTop pick
Researched 26d agoNemotron 3 Super-120B-A12B
- RULER
- 96.33%
- Output (from)
- $0.450 / 1M
Best LLMs for Retrieval-Augmented Generation (2026)
Last refreshed 2026-06-27. Next refresh: weekly.
Compare models for RAG, document QA, retrieval-heavy assistants, and long-context grounding by context window, document benchmarks, tool support, and pricing.
Verdict
Use Nemotron 3 Super-120B-A12B for RAG today.
Llama 4 Scout 17B-16E Instruct is the runner-up; compare RULER against Context.
2ndShortlist
Researched 20d agoLlama 4 Scout 17B-16E Instruct
- Context
- 10m
- Output (from)
- $0.220 / 1M
3rdShortlist
Researched 38d agoGrok 4.20 Multi-Agent
- Context
- 2m
- Output (from)
- $2.50 / 1M
How we rank
RAG picks emphasize the strongest sourced long-document benchmark among tracked RAG needles, QA, and retrieval suites, then context window, then recency.
- Eligibility — Models tagged for the RAG decision task (collections/specialization fit or scores on RULER, ZeroSCROLLs, InfiniteBench, multi-needle, MS MARCO, SQuAD, NaturalQuestions, TriviaQA, etc.).
- Primary ranking — Best score across the RAG benchmark bundle, then larger declared context window, then newer release.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). When headline scores tie within ±0.5 pt (±10 Elo on Chatbot Arena), we pick the canonical SKU by lowest tracked input price, then GA over preview or limited access, then newest `release`. A folded sibling within the benchmark noise band can show a "Tied within margin" chip on that score cell.
- Pricing — Lowest tracked provider input/output where present.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Nemotron 3 Super-120B-A12B Signal used: RULER 96.33% | $0.09 | $0.45 | |
| 2 | Llama 4 Scout 17B-16E Instruct Vision Signal used: Context 10m | $0.08 | $0.22 | |
| 3 | Grok 4.20 Multi-Agent ReasoningVisionTools Signal used: Context 2m | $1.25 | $2.50 | |
| 4 | Gemini 1.5 Pro Signal used: Context 2m | $1.25 | $5.00 | |
| 5 | GPT-5.5 ReasoningVisionTools Signal used: Context 1.05m | $5.00 | $30.00 | |
| 6 | GPT-5.5 Pro ReasoningVisionTools Signal used: Context 1.05m | $30.00 | $180.00 | |
| 7 | GPT-5.4 ReasoningVisionTools Signal used: Context 1.05m | $2.50 | $15.00 | |
| 8 | GPT-5.4 Pro ReasoningVisionTools Signal used: Context 1.05m | $30.00 | $180.00 | |
| 9 | Gemini 3.5 Flash ReasoningVisionTools Signal used: Context 1.05m | $1.50 | $9.00 | |
| 10 | Antigravity Agent PreviewReasoningVision Signal used: Context 1.05m | — | — | |
| 11 | Gemini 3.1 Flash-Lite VisionTools Signal used: Context 1.05m | $0.25 | $1.50 | |
| 12 | Xiaomi MiMo-V2.5-Pro Tools Signal used: Context 1.05m | $0.43 | $0.87 | |
| 13 | Xiaomi MiMo-V2.5 ReasoningVisionTools Signal used: Context 1.05m | $0.14 | $0.28 | |
| 14 | Gemini 2.5 Pro Computer Use Preview PreviewVisionTools Signal used: Context 1.05m | $1.25 | $10.00 | |
| 15 | GPT-4.1 VisionTools Signal used: Context 1.05m | $2.00 | $8.00 | |
| 16 | GPT-4.1 Mini VisionTools Signal used: Context 1.05m | $0.40 | $1.60 | |
| 17 | Fugu ReasoningVisionTools Signal used: Context 1m | — | — | |
| 18 | Fugu Ultra ReasoningVisionTools Signal used: Context 1m | $5.00 | $30.00 | |
| 19 | GLM-5.2 ReasoningTools Signal used: Context 1m | $1.40 | $4.40 | |
| 20 | Claude Fable 5 ReasoningVisionTools Signal used: Context 1m | $10.00 | $50.00 |
Honorable mentions
Next seats in this ranking. Lines below are from each model's stored description in LLMReference seed data—spot-check the model page before relying on a capability claim.
Gemini 1.5 Pro, created by Google DeepMind, is a state-of-the-art multimodal large language model that significantly advances over its predecessors in processing and analyzing large datasets across various formats like text, images, audio, and video. It features a highly extended context window of up to 2 million tokens, allowing it to maintain coherence over lengthy interactions. With over 200 billion parameters, the model excels in tasks requiring nuanced language processing, coding assistance, and advanced reasoning. Integrated into Google's platforms such as Vertex AI, Gemini 1.5 Pro also emphasizes ethical considerations, ensuring safety and appropriateness in AI deployment.
2m
Context
- #5GPT-5.5
GPT-5.5 is OpenAI's fully retrained agentic model, released April 23, 2026. Optimised for agentic coding, computer use, knowledge work, and early scientific research. Achieves 82.7% on Terminal-Bench 2.0 (Codex CLI scaffold), 84.9% on GDPval, 58.6% on SWE-Bench Pro, 93.6% on GPQA Diamond, and 82.6% on SWE-Bench Verified (Vals.ai independent harness). Knowledge cutoff December 2025. Supports reasoning effort levels (none/low/medium/high/xhigh). Context window 1,050,000 tokens with a long-context surcharge above 272K tokens. Model ID: gpt-5.5.
1.05m
Context
GPT-5.5 Pro is OpenAI's premium extra-compute deployment of GPT-5.5, released April 23, 2026. It uses the same underlying weights as GPT-5.5 standard with additional parallel test-time compute for harder tasks. Supports text and image inputs, reasoning effort control, tool use, structured outputs, code execution, a 1,050,000-token context window, and 128K max output. Key datapack rows: Terminal-Bench 2.1 78.2%, SWE-bench Pro 58.6%, GPQA Diamond 93.6%, ARC-AGI-2 high effort 83.3%, BrowseComp Pro compute 90.1%, and FrontierMath Tier 4 39.6%. Official pricing is $30/M input, $180/M output, $10/M batch input, and $45/M batch output; native cached input discount is not listed.
1.05m
Context
Compare Top Picks
Side-by-side comparison of the top picks by price, benchmark, and API access.
Browse Other Categories
Best LLMs for Code GenerationBest AI Agents & Agentic ModelsBest LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for Function Calling & Tool UseCheapest LLM APIs You Can Call Right NowBest Long Context LLMsBest Mainstream LLM APIs, RankedBest LLMs for EnterpriseBest Free LLMs You Can Use Right NowBest LLMs for WritingBest LLMs for MarketingBest LLMs for Customer Support