Seneca-TRBench: leaderboard
Seneca-TRBench evaluates LLM Turkish language proficiency with MCQ structural-linguistics questions and GPT-4o-judged short-answer tasks.
Metric: Combined Score (imported). Source: github.com. Source: benchmarklist.com. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 93.5 | #98 |
| 2 | GPT-5 Nano | 92.9 | #425 |
| 3 | GPT-5 Mini | 92.4 | #186 |
| 4 | Claude Opus 4.1 (20250805) | 90.06 | #132 |
| 5 | Claude Sonnet 4.5 | 88.78 | #142 |
Interactive version: theaggregate.ai/benchmark?slug=seneca-trbench · How It Works · Data refreshed daily, snapshot 2026-10-20.