Home / AI models
The AI index
12 providers, ranked by independent quality (Elo from blind duels). Alongside this, our own assessment, live prices and the context window.
Ranking
Sort by
#ModelElo · 30 daysQuality from blind duels on LMArena: users choose between two anonymous answers. A difference of about 20 points is noticeable, a few points is noise. How we measureTrendEditorial teamOur own assessment on 10 of suitability for professional work, price and privacy. A judgement, not a measurement; that is why it always sits alongside the Elo. How we measurePrice fromContextGDPROur summary of what the provider itself publishes about your data. For a professional tool: whether the data is held in the EU, whether there is a certification or GDPR guarantee, and whether the provider is based in the Netherlands or the EU. For a general model: EU hosting, no training on your data and self-hosting. From Strong to Unknown; Caution only applies to a model with a documented problem. How we measure
1
GeminiGoogle1527+2 Elo8.6$10 /1M~1M tokens2
ClaudeAnthropic1506−1 Elo9,0$20 /1M1M tokens3
KimiMoonshot AI1487−1 Elo7.6$10 /1M1M tokens4
ChatGPTOpenAI1485±0 Elo8.9$50 /1M~1M tokens5
CopilotMicrosoft1485±0 Elo8.3$30 /1MModel-dependent6
QwenAlibaba Cloud1484▲ 5 Elo7,9$6 /1M1M tokens7
GLM (Z.ai)Z.ai (Zhipu AI)1483+3 Elo7,7$1.4 /1M1M tokens8
DeepSeekDeepSeek1475−2 Elo7,4$0.5 /1M1M tokens9
GrokxAI1471−4 Elo7,8$6 /1M500K tokens (Grok 4.7)10
Le Chat (Mistral)Mistral AI1426▲ 11 Elo8,4$2.1 /1M256K tokens11
PerplexityPerplexity AI––8,0$15 /1M200K tokens12
LlamaMeta–±0 Elo7,6$4.25 /1Mtot 10M tokens
GeminiGoogle1527+2 Elo8.6$10 /1M~1M tokens2ClaudeAnthropic1506−1 Elo9,0$20 /1M1M tokens3KimiMoonshot AI1487−1 Elo7.6$10 /1M1M tokens4ChatGPTOpenAI1485±0 Elo8.9$50 /1M~1M tokens5CopilotMicrosoft1485±0 Elo8.3$30 /1MModel-dependent6QwenAlibaba Cloud1484▲ 5 Elo7,9$6 /1M1M tokens7GLM (Z.ai)Z.ai (Zhipu AI)1483+3 Elo7,7$1.4 /1M1M tokens8DeepSeekDeepSeek1475−2 Elo7,4$0.5 /1M1M tokens9GrokxAI1471−4 Elo7,8$6 /1M500K tokens (Grok 4.7)10Le Chat (Mistral)Mistral AI1426▲ 11 Elo8,4$2.1 /1M256K tokens11PerplexityPerplexity AI––8,0$15 /1M200K tokens12LlamaMeta–±0 Elo7,6$4.25 /1Mtot 10M tokensBron: LMArena, OpenRouter · opgehaald 9 november 2026
The full index on one scale
Ordered by quality; height is our editorial score. That is why a higher score sometimes sits further to the right.
#1Gemini#2Claude#3Kimi#4ChatGPT#5Copilot#6Qwen#7GLM (Z.ai)#8DeepSeek#9Grok#10Le Chat (Mistral)#11Perplexity#12Llama
Scale 0 to 10 · editorial score
All individual models
Not the providers but the individual models, ranked by Elo, with price per million tokens. A difference of around 20 points is noticeable; a few points is noise.
| Model | Family | Type | Elo | Price in | Price out | Context |
|---|---|---|---|---|---|---|
| Qwen3.8 Max | Qwen | Flagship | 1484 | – | – | – |
| GPT-5.5 | ChatGPT | Flagship | 1481 | $5 | $30 | 1.050.000 |
| GLM-5.2 | GLM (Z.ai) | Flagship | 1475 | $0.01 | $6.8 | 1.048.576 |
| GLM-5.3 Flash | GLM (Z.ai) | Fast & cheap | 1475 | $0.03 | $0.08 | 1.048.576 |
| Qwen3.7 Max | Qwen | Flagship | 1474 | $1.48 | $4.42 | 1.000.000 |
| Qwen3.7 Max Preview | Qwen | Preview | 1474 | – | – | – |
| GLM-5.1 | GLM (Z.ai) | Balanced | 1465 | $1.4 | $4.4 | 204.800 |
| DeepSeek-V4 Pro | DeepSeek | Most powerful | 1464 | $0.96 | $1.91 | 1.048.576 |
| Qwen3.7 Plus | Qwen | Balanced | 1455 | $0.32 | $1.28 | 1.000.000 |
| DeepSeek-V4 Flash | DeepSeek | Fast & cheap | 1439 | $0.09 | $0.18 | 1.048.576 |
| Qwen3.8 27B | Qwen | Open-weight | 1433 | $0.15 | $1.88 | 1.024.000 |
The playing field in data
All figures based on the same sources, refreshed daily.
1484hoogste Elo · Qwen3.8 Max
GLM-5.3 Flashbest value for money · Elo 1475 for $0.08/1M
$0.08cheapest per 1M output · GLM-5.3 Flash
2,000,000largest context · Grok 4.20
Price versus quality
Top left is the best deal: plenty of quality for little money. The yellow dot is the strongest model.
Code quality
Claude1818Gemini1768ChatGPT1767Copilot1767Kimi1687Qwen1677DeepSeek1664Grok1640GLM (Z.ai)1622Le Chat (Mistral)1563Llama1528
Scale 1450 to 1850 Elo