Ling-2.5-1T: benchmark results
Provider: InclusionAI. Released 2026-02-14. Access: Open.
Aggregate Rating 1641 ± 21, rank #681 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LiveSecBench | 40.46 | Overall Score (%) | 42.9 |
| OneMillion-Bench (CN, Web Search) | 11.5 | Pass rate (%): share of tasks whose expert score reaches the | 36.1 |
| LLM2014 Logic 2026-03 | 29.89 | Median Score | 34.1 |
| LLM2014 Logic 2026-04 | 29.17 | Median Score | 32.5 |
| ClawProBench | 51.19 | Final Score (imported) | 30.4 |
| OneMillion-Bench (CN) | 11 | Pass rate (%): share of tasks whose expert score reaches the | 30 |
| OneMillion-Bench (CN) - Expert Score | 36.7 | Expert score (%): per task, the weighted share of expert-wri | 26.7 |
| OneMillion-Bench | 7.5 | Pass Rate (%) | 18.8 |
| OneMillion-Bench (Web Search) | 6.5 | Pass rate (%): share of tasks whose expert score reaches the | 16.7 |
| OneMillion-Bench (CN, Web Search) - Expert Score | 35.6 | Expert score (%): per task, the weighted share of expert-wri | 13.9 |
| OneMillion-Bench - Expert Score | 33.1 | Expert score (%): per task, the weighted share of expert-wri | 6.7 |
| OneMillion-Bench (Web Search) - Expert Score | 31.2 | Expert score (%): per task, the weighted share of expert-wri | 5.6 |
Interactive version: theaggregate.ai/model?slug=ling-2-5-1t · How It Works · Data refreshed daily, snapshot 2026-11-08.