GPT-4 vs Mistral Small
Comparing GPT-4 and Mistral Small across benchmarks, pricing, and capabilities.
OpenAI · Mistral AI · Updated for 2026
Which is better?
GPT-4 and Mistral Small trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.
On price, Mistral Small is roughly 125.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose GPT-4
- you want predictable pricing at $30.00/M input and $60.00/M output
Choose Mistral Small
- cost matters — it's about 125.0x cheaper per token
- you want the most recent training data — it shipped Sep 2024
- you need open weights you can self-host or fine-tune
At a glance
The differences that matter most.
Individual benchmarks
12 reported for GPT-4 · 0 for Mistral Small
GPT-4 and Mistral Smalldon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, GPT-4 ($30.00/1M tokens) is 150.0x more expensive than Mistral Small ($0.20/1M tokens).
For output processing, GPT-4 ($60.00/1M tokens) is 100.0x more expensive than Mistral Small ($0.60/1M tokens).
In conclusion, GPT-4 is more expensive than Mistral Small.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Both models have the same input context window of 32,768 tokens. Both models can generate responses up to 32,768 tokens.
Input capabilities
Documented input modalities across available providers
GPT-4 supports multimodal inputs, whereas Mistral Small does not.
GPT-4 can handle both text and other forms of data like images, making it suitable for multimodal applications.
GPT-4
Mistral Small
License
Usage and distribution terms
GPT-4 is licensed under a proprietary license, while Mistral Small uses Mistral Research License.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
Mistral Research License
Open weights
Release Timeline
When each model was launched
GPT-4 was released on 2023-06-13, while Mistral Small was released on 2024-09-17.
Mistral Small is 15 months newer than GPT-4.
Jun 13, 2023
3.2 years ago
Sep 17, 2024
2.0 years ago
1.3yr newerKnowledge Cutoff
When training data ends
GPT-4 has a documented knowledge cutoff of 2022-12-31, while Mistral Small's cutoff date is not specified.
We can confirm GPT-4's training data extends to 2022-12-31, but cannot make a direct comparison without Mistral Small's cutoff date.
Dec 2022
—
Provider Availability
GPT-4 is available from Azure, OpenAI. Mistral Small is available from Mistral AI.
GPT-4
Mistral Small
Outputs Comparison
Judge for yourself.
Run your own prompts against GPT-4 and Mistral Small side-by-side, then vote on the output you prefer.
FAQ
Common questions about GPT-4 vs Mistral Small.