LiveK12Bench: leaderboard
Advanced Large Multimodal Models (LMMs) have demonstrated impressive performance in K-12 reasoning tasks, exhibiting great promise as intelligent tutors. Realizing this potential requires models to navigate real-world examinations effectively, yet most existing benchmarks fail to capture the complexity of authentic testing environments. Specifically, most datasets are static, prone to data contami
Metric: Mathematics Acc (self-reported). Source: benchmarklist.com. Saturation forecast: Around June 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 88.3 | #80 |
| 2 | Claude Opus 4.6 | 87.2 | #63 |
| 3 | Gemini 3 Flash | 87.2 | #99 |
| 4 | Kimi K2.5 | 85 | #144 |
| 5 | Claude Sonnet 4.6 | 83.9 | #90 |
| 6 | GPT-5 | 82.7 | #98 |
| 7 | Qwen 3 VL 235B A22B | 82.5 | #238 |
| 8 | GLM-5 | 79.8 | #141 |
| 9 | GPT-5 Mini | 79 | #186 |
| 10 | GPT-4o | 35 | #343 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=livek12bench · How It Works · Data refreshed daily, snapshot 2026-10-20.