TeleMM-2.0: benchmark results
Provider: Other. Access: API.
Aggregate Rating 1750 ± 37, rank #179 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MathVista | 82.8 | Accuracy (%) | 99.5 |
| HallusionBench | 65.7 | Overall Score | 99 |
| AI2D | 89.5 | Accuracy (%) | 98 |
| MM-Vet | 82.8 | Score | 98 |
| OpenCompass Multimodal - Average | 81.1 | Average Score | 97.1 |
| OpenVLM OCRBench | 90.8 | Score (normalized) | 96.4 |
| MMStar | 73.7 | Accuracy (%) | 96.2 |
| OCRBench v2 | 66.2 | Average (imported) | 96.2 |
| OpenCompass Multimodal - MMBench | 87.9 | Score (%) | 96.2 |
| OpenCompass Multimodal - MMMU | 76 | Score (%) | 96.2 |
| OCRBench-V2 (zh) | 66.2 | Score (imported) | 90.3 |
| OCRBench-V2 (en) | 61.8 | Score (imported) | 62.9 |
Interactive version: theaggregate.ai/model?slug=telemm-2-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.