LearnLM 1.5 Pro: benchmark results
Provider: Other.
Aggregate Rating 1618 ± 26, rank #857 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| KMP-Bench (Skills) - Error Diagnosis MR-Score | 69.8 | MR-Score (%) from MR-GSM8K: 0.2 x MCC of the solution-correc | 100 |
| MathTutorBench | 66.33 | Overall Average (imported) | 100 |
| KMP-Bench (Skills) - Error Correction | 94.4 | Correction accuracy (%): share of turn-two corrected solutio | 91.7 |
| KMP-Bench (Skills) - Multi-Turn Problem Solving | 87.7 | Accuracy (%) on the final turn of a three-turn sequence (a s | 91.7 |
| KMP-Bench (Skills) - Similar Problem Generation | 75 | Pass rate (%) of generated similar practice problems and sol | 75 |
| KMP-Bench (Skills) - Error Identification F1 | 74.6 | F1 (%) for turn one of the error task, judging whether a stu | 72.7 |
| KMP-Bench (Skills) - Follow-up Problem Generation | 77 | Pass rate (%) of generated follow-up problems and solutions | 66.7 |
| AI for Education Pedagogy - Technology | 80.19 | Accuracy (%) | 56.4 |
| AI for Education Pedagogy - Social studies | 80 | Accuracy (%) | 55.9 |
| AI for Education Pedagogy - Primary | 83.1 | Accuracy (%) | 51 |
| AI for Education Pedagogy - Maths | 76.98 | Accuracy (%) | 49 |
| AI for Education Pedagogy - Secondary | 77.04 | Accuracy (%) | 48.4 |
Interactive version: theaggregate.ai/model?slug=learnlm-1-5-pro · How It Works · Data refreshed daily, snapshot 2026-11-08.