Mi:dm K 2.5 Pro: benchmark results
Provider: KT. Released 2025-12-28. Access: API.
Aggregate Rating 1609 ± 26, rank #929 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA TAU-2 Bench | 86.55 | Accuracy (%) | 79.6 |
| Tau2-Bench Telecom | 86.55 | Success Rate (%) | 79.3 |
| AA LiveCodeBench | 65.61 | Pass@1 (%) | 73.4 |
| AA MMLU-Pro | 80.94 | Accuracy (%) | 72.7 |
| AA AIME 2025 | 76.67 | Accuracy (%) | 71.4 |
| AA IFBench | 49.32 | Accuracy (%) | 58.7 |
| AA GPQA Diamond | 70.1 | Accuracy (%) | 48.9 |
| AA Global-MMLU-Lite - Korean | 83.5 | Accuracy (%) | 47.3 |
| AA Global-MMLU-Lite - Italian | 87.25 | Accuracy (%) | 46.4 |
| AA Global-MMLU-Lite - Chinese | 85.08 | Accuracy (%) | 44.5 |
| AA Humanity's Last Exam | 8.06 | Accuracy (%) | 44 |
| AA Global-MMLU-Lite - English | 88.75 | Accuracy (%) | 35 |
Interactive version: theaggregate.ai/model?slug=mi-dm-k-2-5-pro · How It Works · Data refreshed daily, snapshot 2026-11-08.