LIBRA - LongContextMultiQ * — leaderboard
Metric: Dataset Total Score (%). Source: huggingface.co. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 30B A3B 2507 Instruct | 45.96 |
| 2 | Llama 3.1 8B Instruct | 40.68 |
| 3 | Qwen 3.5 35B A3B | 39.04 |
| 4 | Qwen 3.5 122B A10B | 38.14 |
| 5 | Qwen 3.5 9B | 37.04 |
| 6 | Phi-3.5-mini-instruct | 34.92 |
| 7 | Qwen 3.5 4B | 34.9 |
| 8 | Qwen 3.5 2B | 33.39 |
| 9 | Qwen 3.5 0.8B | 31.73 |
| 10 | LFM2.5-1.2B Instruct | 21.2 |
Interactive version: theaggregate.ai/benchmark?slug=libra-longcontextmultiq-star · How the rankings work · Data refreshed daily, snapshot 2026-07-22.