JT-Think: benchmark results
Provider: China Mobile. Access: API.
Aggregate Rating 1654 ± 39, rank #595 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenCompass Research - IFEval | 94.6 | Score (%) | 98.9 |
| OpenCompass Research - MMLU-Pro | 85.6 | Score (%) | 87.2 |
| OpenCompass Research - HLE | 14.4 | Score (%) | 56.4 |
| OpenCompass Research - GPQA Diamond | 77.7 | Score (%) | 51.1 |
| OpenCompass | 67.2 | Average Score | 47.9 |
| OpenCompass Research - LiveCodeBench v6 | 64.9 | Score (%) | 44.7 |
| OpenCompass Research - AIME 2025 | 65.9 | Score (%) | 19.1 |
Interactive version: theaggregate.ai/model?slug=jt-think · How It Works · Data refreshed daily, snapshot 2026-11-08.