OpenLearnLM - Skills - Assessment: leaderboard
Assessment tasks from the OpenLearnLM Benchmark (Lee et al., 2026): generated evaluator scenarios for diagnostic, formative and summative assessment, such as rubric application and item design. An LLM judge, not named in the paper, scores each answer on a scenario-specific 1-10 rubric; the score is the mean, and higher is better.
Metric: Rubric Score (1-10; LLM judge, scenario-specific rubrics, Assessment center). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 8.56 | #152 |
| 2 | DeepSeek V3.2 | 8.52 | #403 |
| 3 | Grok 4.1 Fast | 8.49 | #426 |
| 4 | Kimi K2 (Thinking) | 8.46 | #435 (Kimi K2) |
| 5 | Gemini 3 Pro | 8.38 | #135 |
| 6 | GLM-4.7 | 8.28 | #365 |
| 7 | GPT-5.2 | 8.22 | #172 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=openlearnlm-skills-assessment · How It Works · Data refreshed daily, snapshot 2026-11-12.