1stTop pick
Researched 4d agoClaude Opus 4.7
- GPQA Diamond
- 94.2%
- Output (from)
- $25.00 / 1M
Best Reasoning LLMs (2026)
Last refreshed 2026-05-18. Next refresh: weekly.
Top AI models for complex reasoning, math, and step-by-step problem solving, ranked by sourced reasoning benchmarks and release freshness.
Top three picks
Opinionated short stack for this category — scroll for the full leaderboard, pricing, and compare links.
2ndShortlist
Researched 8d agoGPT-5.5
- GPQA Diamond
- 93.6%
- Output (from)
- $30.00 / 1M
3rdShortlist
Researched 8d agoGPT-5.5 Pro
- GPQA Diamond
- 93.6%
- Output (from)
- $180.00 / 1M
How we rank
Reasoning boards prioritize GPQA Diamond scores, favoring models explicitly tagged for reasoning or unusually strong GPQA.
- Eligibility — Reasoning flag or GPQA Diamond above the editorial floor used on this page.
- Primary ranking — GPQA Diamond (higher is better), 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 — Reasoning tiers are often priced separately — confirm provider SKUs.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Claude Mythos Preview PreviewReasoningVisionTools GPQA Diamond: 94.6% | — | — | |
| 2 | Gemini 3.1 Pro Preview PreviewVisionTools GPQA Diamond: 94.3% | $2.00 | $12.00 | |
| 3 | Claude Opus 4.7 ReasoningVisionTools GPQA Diamond: 94.2% | $5.00 | $25.00 | |
| 4 | GPT-5.5 ReasoningVisionTools GPQA Diamond: 93.6% | $5.00 | $30.00 | |
| 5 | GPT-5.5 Pro ReasoningVisionTools GPQA Diamond: 93.6% | $30.00 | $180.00 | |
| 6 | GPT-5.4 ReasoningTools GPQA Diamond: 92% | $2.50 | $15.00 | |
| 7 | Claude Opus 4.6 ReasoningVisionTools GPQA Diamond: 91.3% | $5.00 | $25.00 | |
| 8 | Kimi K2.6 ReasoningVisionTools GPQA Diamond: 90.5% | $0.75 | $3.50 | |
| 9 | DeepSeek V4 Pro ReasoningTools GPQA Diamond: 90.1% | $0.43 | $0.87 | |
| 10 | Claude Sonnet 4.6 ReasoningVisionTools GPQA Diamond: 89.9% | $3.00 | $15.00 | |
| 11 | Muse Spark ReasoningVisionTools GPQA Diamond: 89.5% | — | — | |
| 12 | Qwen3.5-397B-A17B ReasoningTools GPQA Diamond: 89.3% | $0.39 | $2.34 | |
| 13 | Trinity-Large-Thinking ReasoningTools GPQA Diamond: 89.2% | $0.22 | $0.85 | |
| 14 | ByteDance Doubao Seed 2.0 Pro Tools GPQA Diamond: 88.9% | — | — | |
| 15 | DeepSeek V4 Flash ReasoningTools GPQA Diamond: 88.1% | $0.14 | $0.28 | |
| 16 | Kimi K2.5 Tools GPQA Diamond: 87.9% | $0.44 | $2.00 | |
| 17 | Qwen3.6-27B ReasoningVisionTools GPQA Diamond: 87.8% | $0.32 | $3.20 | |
| 18 | o3 Reasoning GPQA Diamond: 87.7% | $2.00 | $8.00 | |
| 19 | MiniMax M2.7 ReasoningTools GPQA Diamond: 87.4% | $0.30 | $1.20 | |
| 20 | Gemini 3.1 Flash-Lite VisionTools GPQA Diamond: 86.9% | $0.25 | $1.50 |
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.
- #4GPT-5.4
GPT-5.4 is OpenAI's flagship frontier reasoning model, released March 5, 2026. It incorporates advances from GPT-5.3-Codex for coding and agentic workflows, and adds 'Thinking' mode with editable reasoning plans. Key capabilities include computer use (navigating interfaces via Playwright), image understanding and generation integration, full-stack web app generation, tool calling, and deep research. Knowledge cutoff is August 31, 2025. Model ID: gpt-5.4.
92%
GPQA Diamond
Claude Opus 4.6 available on AWS Bedrock
91.3%
GPQA Diamond
Kimi K2.6 is Moonshot AI's latest agentic reasoning model, launched April 13 2026 as a code preview for Kimi Code subscribers. Built on a 1-trillion-parameter MoE architecture (32B active, 384 experts), it inherits K2.5's 256K context window and adds enhanced reliability for long-horizon agentic workflows — supporting 200–300 sequential tool calls without drift. Optimized for coding, multi-step agent planning, and vision-assisted tasks such as processing screenshots, PDFs, and spreadsheets.
90.5%
GPQA Diamond
Compare Top Picks
Browse Other Categories
Best LLMs for Code GenerationBest LLMs for RAGBest AI Agents & Agentic ModelsBest LLMs for ClassificationBest Open Source LLMsBest Multimodal / Vision LLMsBest 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