Models, measured side by side
GPT-5.2 Pro vs Mistral Medium 3.5
Compare GPT-5.2 Pro, Mistral Medium 3.5 by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
GPT-5.2 Pro
$1,260 / mo
Mistral Medium 3.5
$68 / mo
Performance comparison
GPT-5.2 Pro
Not listed
Mistral Medium 3.5
14.2
Overview
| Overview | GPT-5.2 Pro | Mistral Medium 3.5 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Released | 2025-12 | 2026-04-30 |
| Status | Active | Active |
| Input formats | imagetextfile | textimagefile |
| Output formats | text | text |
Provider
- GPT-5.2 Pro
- OpenAI
- Mistral Medium 3.5
- Mistral AI
Released
- GPT-5.2 Pro
- 2025-12
- Mistral Medium 3.5
- 2026-04-30
Status
- GPT-5.2 Pro
- Active
- Mistral Medium 3.5
- Active
Input formats
- GPT-5.2 Pro
- imagetextfile
- Mistral Medium 3.5
- textimagefile
Output formats
- GPT-5.2 Pro
- text
- Mistral Medium 3.5
- text
Pricing & capacity
| Pricing & capacity | GPT-5.2 Pro | Mistral Medium 3.5 |
|---|---|---|
| Input / 1M tokens | $21 | $1.50 |
| Output / 1M tokens | $168 | $7.50 |
| Monthly cost | $1,260 | $68 |
| Context window | 400K | 262K |
| Maximum output | 128K | 210K |
Input / 1M tokens
- GPT-5.2 Pro
- $21
- Mistral Medium 3.5
- $1.50
Output / 1M tokens
- GPT-5.2 Pro
- $168
- Mistral Medium 3.5
- $7.50
Monthly cost
- GPT-5.2 Pro
- $1,260
- Mistral Medium 3.5
- $68
Context window
- GPT-5.2 Pro
- 400K
- Mistral Medium 3.5
- 262K
Maximum output
- GPT-5.2 Pro
- 128K
- Mistral Medium 3.5
- 210K
Benchmarks & performance
| Benchmarks & performance | GPT-5.2 Pro | Mistral Medium 3.5 |
|---|---|---|
| Arena Elo | 1,255 | Not listed |
| MMLU-Pro | 82.8% | Not listed |
| Intelligence Index | Not listed | 14.2 |
| GPQA | Not listed | 74.8% |
| Humanity’s Last Exam | Not listed | 13.8% |
| SciCode | Not listed | 40.2% |
| Output speed | Not listed | 166 tokens/s |
| Time to first token | Not listed | 2.21 s |
| DesignArena rating | Not listed | 1,125 |
| DesignArena win rate | Not listed | 41.1% |
Arena Elo
- GPT-5.2 Pro
- 1,255
- Mistral Medium 3.5
- Not listed
MMLU-Pro
- GPT-5.2 Pro
- 82.8%
- Mistral Medium 3.5
- Not listed
Intelligence Index
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 14.2
GPQA
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 74.8%
Humanity’s Last Exam
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 13.8%
SciCode
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 40.2%
Output speed
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 166 tokens/s
Time to first token
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 2.21 s
DesignArena rating
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 1,125
DesignArena win rate
- GPT-5.2 Pro
- Not listed
- Mistral Medium 3.5
- 41.1%
Tools & features
| Tools & features | GPT-5.2 Pro | Mistral Medium 3.5 |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Deterministic seed | Supported | Supported |
Function calling
- GPT-5.2 Pro
- Supported
- Mistral Medium 3.5
- Supported
Structured outputs
- GPT-5.2 Pro
- Supported
- Mistral Medium 3.5
- Supported
JSON mode
- GPT-5.2 Pro
- Supported
- Mistral Medium 3.5
- Supported
Reasoning
- GPT-5.2 Pro
- Supported
- Mistral Medium 3.5
- Supported
Deterministic seed
- GPT-5.2 Pro
- Supported
- Mistral Medium 3.5
- Supported
API & availability
| API & availability | GPT-5.2 Pro | Mistral Medium 3.5 |
|---|---|---|
| API identifier | gpt-5.2-pro | mistral-medium-3-5 |
| API providers | OpenAI | Not listed |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- GPT-5.2 Pro
gpt-5.2-pro- Mistral Medium 3.5
mistral-medium-3-5
API providers
- GPT-5.2 Pro
- OpenAI
- Mistral Medium 3.5
- Not listed
Prices checked
- GPT-5.2 Pro
- Oct 8, 2026
- Mistral Medium 3.5
- Oct 8, 2026
About the models
GPT-5.2 Pro
GPT-5.2 with extra compute for the most demanding problems. No cached-input discount.
Full pricing & detailsMistral Medium 3.5
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
Full pricing & detailsComparison FAQ
GPT-5.2 Pro: $21 input and $168 output per million tokens. Mistral Medium 3.5: $1.50 input and $7.50 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.