1stTop pick
Researched 11d agoKimi K3
- GPQA Diamond
- 93.5%
- Output (from)
- $15.00 / 1M
Best Open Source LLMs (2026)
Last refreshed 2026-09-01. Next refresh: weekly.
The best open-weight LLMs in 2026, ranked by benchmark scores. Run locally, self-host, or deploy on your own infra — no API key required.
Release watch. Nemotron-Labs-Diffusion from NVIDIA, including 3B, 8B, and 14B diffusion language model variants.
Verdict
Use Kimi K3 for self-hosted open-weight use today.
Qwen3.8-Max is the runner-up, 0.9 points back on GPQA Diamond.
2ndShortlist
Researched 11d agoQwen3.8-Max
- GPQA Diamond
- 92.6%
- Output (from)
- $6.00 / 1M
3rdShortlist
Researched 11d agoQwen3.8-27B
- GPQA Diamond
- 89.2%
- Output (from)
- $3.00 / 1M
How we rank
Open-weight boards emphasize GPQA Diamond (harder to game than broad MMLU), then MMLU, then recency.
- Eligibility — Models marked with supported open licenses/flags in seed data.
- Primary ranking — GPQA Diamond, then MMLU, 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 — Hosted open-weight pricing still varies wildly — use the rate card column for apples-to-apples.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Kimi K3 ReasoningVisionTools GPQA Diamond: 93.5% | $3.00 | $15.00 | |
| 2 | MiniMax M3 ReasoningVisionTools GPQA Diamond: 92.9% | $0.30 | $1.20 | |
| 3 | Qwen3.8-Max ReasoningVisionTools GPQA Diamond: 92.6% | $2.00 | $6.00 | |
| 4 | Qwen3.6-Max Vision GPQA Diamond: 91.8% | — | — | |
| 5 | Qwen3.8-Flash-Next ReasoningVision GPQA Diamond: 91.7% | — | — | |
| 6 | GLM-5.2 ReasoningTools GPQA Diamond: 91.2% | $1.40 | $4.40 | |
| 7 | Kimi K2.6 ReasoningVisionTools GPQA Diamond: 90.5% | $0.73 | $3.40 | |
| 8 | Qwen3.6-Plus VisionTools GPQA Diamond: 90.4% | $0.33 | $1.95 | |
| 9 | DeepSeek V4 Pro ReasoningTools GPQA Diamond: 90.1% | $0.43 | $0.87 | |
| 10 | Qwen3.5-397B-A17B ReasoningVisionTools GPQA Diamond: 89.3% | $0.39 | $2.34 | |
| 11 | Qwen3.8-27B ReasoningVisionTools GPQA Diamond: 89.2% | $0.50 | $3.00 | |
| 12 | Trinity-Large-Thinking ReasoningTools GPQA Diamond: 89.2% | $0.22 | $0.85 | |
| 13 | Qwen3.5-Plus Vision GPQA Diamond: 88.4% | $0.30 | $1.80 | |
| 14 | Ring-2.6-1T ReasoningTools GPQA Diamond: 88.27% | $0.07 | $0.63 | |
| 15 | DeepSeek V4 Flash ReasoningTools GPQA Diamond: 88.1% | $0.06 | $0.12 | |
| 16 | Qwen3.6-27B ReasoningVisionTools GPQA Diamond: 87.8% | $0.32 | $3.20 | |
| 17 | DeepSeek V3 0324 GPQA Diamond: 87.6% | $0.27 | $1.12 | |
| 18 | MiniMax M2.7 ReasoningTools GPQA Diamond: 87.4%Tied within margin | $0.28 | $1.20 | |
| 19 | Hunyuan Hy3 Preview PreviewReasoningTools GPQA Diamond: 87.2% | $0.07 | $0.26 | |
| 20 | GLM-5.1 ReasoningTools GPQA Diamond: 86.2% | $1.05 | $3.50 |
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.
Arcee AI's flagship 400B sparse MoE reasoning model with 13B active parameters per token. Trained on 20T tokens with a STEM-focused curriculum. Designed for agentic workflows, chain-of-thought reasoning, and long-context tasks up to 256K tokens (BF16 API). Open-source under Apache 2.0. Available via Arcee AI API.
89.2%
GPQA Diamond
Qwen3.5-Plus is the flagship commercial API model of the Qwen3.5 native vision-language series, delivering outstanding performance comparable to state-of-the-art models with significant leaps in both pure-text and multimodal capabilities compared to the Qwen3 series.
88.4%
GPQA Diamond
Ring-2.6-1T is InclusionAI's MIT-licensed trillion-parameter MoE reasoning model for agent workflows, engineering tasks, scientific analysis, and enterprise automation. It supports high and xhigh reasoning effort modes and entered OpenRouter's Programming top 10 in the 2026-05-18 audit.
88.27%
GPQA Diamond
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 LLMs for RAGBest LLMs for Agents & Coding (2026)Best LLMs for ClassificationBest Multimodal / Vision LLMsBest LLM for Translation in 2026Best AI Image Models in 2026Best AI Video Models in 2026Best LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for JSON / 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