Mi:dm K 2.5 Pro
Intelligence
23.1
#231/523
Coding
12.6
#302/429
Math
76.7
#77/265
Speed
—
Pricing
—
Mi:dm K 2.5 Pro is Korea Telecom’s latest model designed for advanced computational tasks. It features a high Math Index of 76.7, making it suitable for mathematical problem-solving, but it currently processes at 0 tokens per second. It is priced at $0 per million tokens, targeting professional users.
When to Use Mi:dm K 2.5 Pro
✓ Best For
- Mathematical modeling and simulations.
- Data analysis requiring complex calculations.
- Professional applications in research and development.
✗ Not Ideal For
- Real-time applications due to zero processing speed.
- Users needing immediate output or response times.
How Mi:dm K 2.5 Pro Compares
Intelligence Index · Higher is better
Z AIAmazonKorea TelecomxAIOpenAI
Benchmark Profile
Coding Index
AnthropicAlibabaKorea TelecomAmazon
Math Index
MBZUAI Institute of Foundation ModelsAllen Institute for AIKorea TelecomNVIDIADeepSeek
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 23.1 | |
| Coding Index | 12.6 | |
| Math Index | 76.7 | |
| MMLU-Pro | 809% | |
| GPQA | 701% | |
| LiveCodeBench | 656% | |
| HLE | 77% | |
| SciCode | 33.2% | |
| IFBench | 49.3% | |
| LCR | 9% | |
| TerminalBench Hard | 2.3% | |
| Tau2 | 86.5% | |
| AIME 2025 | 76.7% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Mi:dm K 2.5 Pro released?
Mi:dm K 2.5 Pro was released on December 11, 2025.
Who created Mi:dm K 2.5 Pro?
Mi:dm K 2.5 Pro was created by Korea Telecom.
How intelligent is Mi:dm K 2.5 Pro?
Mi:dm K 2.5 Pro scores 23 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 13).
How verbose is Mi:dm K 2.5 Pro?
When evaluated on the Intelligence Index, Mi:dm K 2.5 Pro generated 62M output tokens, which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 23M).
Is Mi:dm K 2.5 Pro a reasoning model?
Yes, Mi:dm K 2.5 Pro is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Mi:dm K 2.5 Pro support?
Mi:dm K 2.5 Pro supports text input.
What output modalities does Mi:dm K 2.5 Pro support?
Mi:dm K 2.5 Pro supports text output.
Can Mi:dm K 2.5 Pro process images?
No, Mi:dm K 2.5 Pro does not support image input. It can only process text.
Is Mi:dm K 2.5 Pro multimodal?
No, Mi:dm K 2.5 Pro is not multimodal. It only supports text input.
What is the context window of Mi:dm K 2.5 Pro?
Mi:dm K 2.5 Pro has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Mi:dm K 2.5 Pro open source?
No, Mi:dm K 2.5 Pro is proprietary. The model weights are not publicly available.
How many parameters does Mi:dm K 2.5 Pro have?
Mi:dm K 2.5 Pro has 32 billion parameters.
How does Mi:dm K 2.5 Pro perform on benchmarks?
Mi:dm K 2.5 Pro achieves a score of 23 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Mi:dm K 2.5 Pro available via API?
Check the providers page for current API availability.
Where can I use Mi:dm K 2.5 Pro?
Visit the providers page to see availability.
