The leading models side by side. Measured independently.
From frontier models to open models for your own data center: how capable, how fast and how expensive the leading models are. Artificial Analysis measured them; we put them in context.
Compare models
Strength, speed and price. Rarely all in one model.
Filter and sort by what matters for your use case: strength, speed, price or running in your own data center. Artificial Analysis measured all values independently, so you choose the model by your task, not by the vendor.
52 of 52 models · sorted by Intelligence
| Rank | Model | Coding | |||
|---|---|---|---|---|---|
| 01 | Claude Opus 5.5Anthropic | Intelligence 57.6 | Codingnot measured | Speed97Tokens/s | Price |
| 02 | Claude Sonnet 5.5Anthropic | Intelligence 56.0 | Codingnot measured | Speed128Tokens/s | Price |
| 03 | Claude Fable 5.1Anthropic | Intelligence 53.4 | Coding81.6 | Speed61Tokens/s | Price |
| 04 | GPT-6 AstraOpenAI | Intelligence 52.7 | Coding76.9 | Speed63Tokens/s | Price |
| 05 | Gemini 4 ArgonGoogle | Intelligence 52.6 | Codingnot measured | Speednot measured | Price |
| 06 | GPT-6.1 SolOpenAI | Intelligence 51.8 | Codingnot measured | Speed58Tokens/s | Price |
| 07 | Claude Opus 5Anthropic | Intelligence 50.8 | Coding78.0 | Speed57Tokens/s | Price |
| 08 | Muse Spark 1.3Meta | Intelligence 48.1 | Codingnot measured | Speed187Tokens/s | Price |
| 09 | GPT-6 SolOpenAI | Intelligence 47.6 | Codingnot measured | Speed110Tokens/s | Price |
| 10 | GPT-5.6 SolOpenAI | Intelligence 47.0 | Coding77.4 | Speed97Tokens/s | Price |
| 11 | Grok 4.7SpaceXAI | Intelligence 46.4 | Codingnot measured | Speed92Tokens/s | Price |
| 12 | MiMo-V2.6-ProXiaomi | Intelligence 46.3 | Codingnot measured | Speed45Tokens/s | Price |
| 13 | Qwen3.8 MaxAlibaba | Intelligence 45.4 | Codingnot measured | Speed37Tokens/s | Price |
| 14 | GLM-5.3Z.aiOpen weightsOn-prem available | Intelligence 44.8 | Coding74.8 | Speed75Tokens/s | Price |
| 15 | Kimi K3Moonshot AIOpen weightsOn-prem available | Intelligence 43.6 | Coding76.2 | Speed52Tokens/s | Price |
| 16 | GPT-5.6 TerraOpenAI | Intelligence 42.1 | Coding76.7 | Speed125Tokens/s | Price |
| 17 | Claude Opus 4.8Anthropic | Intelligence 41.8 | Coding74.3 | Speed64Tokens/s | Price |
| 18 | GLM-5.3 FlashZ.ai | Intelligence 41.8 | Coding71.5 | Speed53Tokens/s | Price |
| 19 | Gemini 3.8 FlashGoogle | Intelligence 40.9 | Coding76.3 | Speed242Tokens/s | Price |
| 20 | Claude Opus 4.7Anthropic | Intelligence 40.7 | Coding73.6 | Speednot measured | Price |
| 21 | Qwen3.8 2.4T A95BAlibaba | Intelligence 39.9 | Codingnot measured | Speed39Tokens/s | Price |
| 22 | Qwen3.8-Flash-NextAlibaba | Intelligence 39.8 | Codingnot measured | Speed55Tokens/s | Price |
| 23 | DeepSeek V4.1 FlashDeepSeek | Intelligence 39.5 | Codingnot measured | Speed222Tokens/s | Price |
| 24 | GPT-5.4OpenAI | Intelligence 39.0 | Coding71.1 | Speednot measured | Price |
| 25 | GPT-5.5OpenAI | Intelligence 38.4 | Coding74.9 | Speed104Tokens/s | Price |
| 26 | Claude Sonnet 5AnthropicOpen weightsOn-prem available | Intelligence 38.2 | Coding71.5 | Speed86Tokens/s | Price |
| 27 | GPT-6 LunaOpenAIOpen weightsOn-prem available | Intelligence 38.1 | Codingnot measured | Speed147Tokens/s | Price |
| 28 | MiMo-V2.6-FlashXiaomiOpen weightsOn-prem available | Intelligence 37.9 | Codingnot measured | Speed62Tokens/s | Price |
| 29 | GPT-5.6 LunaOpenAIOpen weightsOn-prem available | Intelligence 37.3 | Coding71.4 | Speed128Tokens/s | Price |
| 30 | DeepSeek V4 Pro 0813DeepSeekOpen weightsOn-prem available | Intelligence 36.0 | Codingnot measured | Speed99Tokens/s | Price |
| 31 | DeepSeek V4 Flash VisionDeepSeekOpen weightsOn-prem available | Intelligence 34.8 | Codingnot measured | Speed232Tokens/s | Price |
| 32 | Qwen3.8 27BAlibabaOpen weightsOn-prem available | Intelligence 33.7 | Coding68.1 | Speed47Tokens/s | Price |
| 33 | Gemini 3.5 FlashGoogle | Intelligence 32.6 | Coding70.1 | Speed335Tokens/s | Price |
| 34 | Claude Opus 4.6Anthropic | Intelligence 31.9 | Codingnot measured | Speednot measured | Price |
| 35 | Claude Sonnet 4.6Anthropic | Intelligence 30.1 | Coding63.0 | Speed46Tokens/s | Price |
| 36 | Gemini 3 ProGoogle | Intelligence 28.0 | Codingnot measured | Speednot measured | Price |
| 37 | GPT-5.1OpenAI | Intelligence 24.7 | Coding49.4 | Speednot measured | Price |
| 38 | GPT-5OpenAIOpen weightsOn-prem available | Intelligence 23.0 | Coding37.8 | Speed129Tokens/s | Price |
| 39 | Qwen3.6 27BAlibabaOpen weightsOn-prem available | Intelligence 21.4 | Coding53.7 | Speed56Tokens/s | Price |
| 40 | Gemini 2.5 ProGoogleOpen weightsOn-prem available | Intelligence 16.1 | Coding33.3 | Speed136Tokens/s | Price |
| 41 | Gemma 4 31BGoogle | Intelligence 14.7 | Coding43.4 | Speed36Tokens/s | Pricenot measured |
| 42 | Qwen3 VL 235BAlibaba | Intelligence 13.4 | Codingnot measured | Speednot measured | Price |
| 43 | Gemini 2.5 FlashGoogle | Intelligence 13.1 | Codingnot measured | Speednot measured | Price |
| 44 | GPT-4.1OpenAI | Intelligence 12.7 | Codingnot measured | Speednot measured | Price |
| 45 | gpt-oss-120bOpenAI | Intelligence 11.6 | Coding30.4 | Speed197Tokens/s | Price |
| 46 | Mistral Large 3Mistral | Intelligence 9.3 | Coding20.1 | Speed83Tokens/s | Price |
| 47 | gpt-oss-20bOpenAI | Intelligence 9.0 | Coding20.7 | Speed188Tokens/s | Price |
| 48 | Gemini 2.5 Flash-LiteGoogle | Intelligence 8.5 | Codingnot measured | Speednot measured | Price |
| 49 | GPT-4oOpenAI | Intelligence 8.4 | Codingnot measured | Speednot measured | Price |
| 50 | Llama 3.3 70BMeta | Intelligence 7.7 | Coding11.9 | Speed94Tokens/s | Price |
| 51 | GPT-4o miniOpenAI | Intelligence 6.7 | Coding11.4 | Speednot measured | Price |
| 52 | Gemma 3 27BGoogle | Intelligence 4.9 | Coding10.1 | Speednot measured | Pricenot measured |
Source: Artificial Analysis (artificialanalysis.ai), as of 6 October 2026. For models with adjustable reasoning effort, the measurement at high or maximum reasoning effort applies. If a value is missing, Artificial Analysis did not measure it; we do not estimate.
Performance vs. price
Each dot is a model: the higher, the stronger; the further right, the more expensive. The efficiency frontier connects the models that deliver more than any cheaper one.
- Anthropic
- OpenAI
- OpenAI
- Meta
- SpaceXAI
- Xiaomi
- Alibaba
- Z.ai
- Moonshot AI
- OpenAI
- DeepSeek
- OpenAI
- OpenAI
- OpenAI
- Mistral
- Proprietary
- Open weights
- Efficiency frontier
Hover over a dot or click it: name and values appear in the panel below.
Claude Opus 5.5
- Intelligence
- 57.6
- Coding
- not measured
- Speed
- 97Tokens/s
- Price
Not plotted (price or index not measured): Gemma 4 31B, Gemma 3 27B. Source: Artificial Analysis (artificialanalysis.ai), as of 6 October 2026.
How to read the values
Intelligence Index
The independent rating by Artificial Analysis combines several tests of knowledge, reasoning, math and coding into a single number. Higher is better. The Coding Index measures coding alone.
Speed
How many tokens a model generates per second, measured at the provider. A token is part of a word. In your own data center, speed depends on your hardware.
Price tier
The list price per million tokens at the providers, grouped into five tiers. More bars means more expensive. Your terms depend on the deployment and are stated in your quote.
On-prem capable
The model weights are openly published. The model can run on your own infrastructure or in a sovereign environment.
Open weights and on-prem
Models with open weights. Can run in your own data center.
Many of these models are published with open weights. For organizations such as banks, insurers, law firms, hospitals or public authorities, this means the model runs where the data lives.
Model choice
You decide which model does the work. Per group, per task, with your own key if you want.
You decide in the neuland.ai HUB which model handles a task. Admins approve models per group; Auto mode or the choice in chat handles the rest.
- Auto modeEach message goes to a suitable model based on its complexity, only among those approved for the group. In Sales, a fast model summarizes the call notes, while the strongest model the group may use analyzes a long annual report.
- Free choice in chatAnyone who wants to can choose for themselves, even mid-chat, and compare the answers of two models side by side.
- Bring your own keysWith Bring Your Own Key (BYOK), you use existing contracts with model providers: you store your own API key in the neuland.ai HUB, and model usage then runs through your own contract.
- Switch without rebuildingWhen a stronger model arrives in the neuland.ai HUB, admins approve it for a group. From then on, the group’s agents work with it, without anyone rebuilding them.
FAQ
What customers ask first about the models.
It depends on the task. Claude Opus 5.5 currently leads the Intelligence Index (57.6), closely followed by Claude Sonnet 5.5 (56.0). For a quick summary, a model like Gemini 3.5 Flash at 335 tokens per second, the fastest in this overview, is often enough, and gpt-oss-120b sits in the lowest price tier and even runs in your own data center. Auto mode makes this trade-off for every message.
All models with open weights, marked as on-prem capable in the overview. These include Qwen3.8 27B, gpt-oss-120b, Mistral Large 3, Llama 3.3 70B and Gemma 4 31B, as well as stronger open models such as MiMo-V2.6-Pro, GLM-5.3, Kimi K3 or DeepSeek V4.1 Flash. Proprietary models such as Claude, GPT or Gemini are connected via their provider’s cloud. We work out with you which hardware an open model needs as part of the deployment concept.
No. Your data is never used to train language models and stays within your company context, regardless of which model you use.
Yes, via Bring Your Own Key (BYOK). If you already have a contract with a model provider, you store your own API key in the neuland.ai HUB. Model usage then runs through your own contract.
As of September 29, 2026. The values come from Artificial Analysis, an independent provider of model comparisons that continuously updates its measurements. If a value is missing, Artificial Analysis has not measured it for this model; we do not estimate.
Because the price of a request in the neuland.ai HUB depends on the deployment: through a provider’s cloud, through your own contract or on your own hardware, the math is different each time. The price tier therefore only shows how expensive the models are relative to each other, based on the providers’ list prices per million tokens. We prepare your quote based on your use case; details in the pricing overview.
The independent rating by Artificial Analysis combines several tests of knowledge, reasoning, math and coding into a single number. Higher is better. The Coding Index measures coding alone.
How many tokens a model generates per second, measured at the provider. A token is part of a word. In your own data center, speed depends on your hardware.
Admins approve models per group. Anyone who wants to can then choose in chat, even mid-conversation, and compare the answers of two models side by side; otherwise Auto mode makes the choice.
The model weights are publicly released, for example on Hugging Face. Such models can run on your own infrastructure or in a sovereign environment.
The right model for each task. We choose it with you.
You bring your tasks, we put the numbers next to them: which model is strong enough, which is fast enough and which has to run in your own data center.
After your request
- 01You name your tasks and protection needs
- 02We assign suitable models to each task
- 03You receive the selection per department as the basis for your onboarding plan