Valley-Eagle-7B: benchmark results
Provider: ByteDance. Released 2024-12-23. Access: Open.
Aggregate Rating 1410 ± 30, rank #5618 of 10916 rated models, from 537 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MEGA-Bench Task - Code Retrieval | 50 | Task Score (%) | 100 |
| MEGA-Bench Task - Bridge Strategies Expert | 45.7 | Task Score (%) | 97.7 |
| MEGA-Bench Task - GUI Chat Hard | 68.8 | Task Score (%) | 97.7 |
| MEGA-Bench Task - Weather Info Parsing | 93.3 | Task Score (%) | 93 |
| MEGA-Bench Task - LLaVAGuard | 71.4 | Task Score (%) | 91.9 |
| MEGA-Bench Task - Stock Info Parsing | 97.5 | Task Score (%) | 91.9 |
| MEGA-Bench Task - Graph Hamiltonian Path | 41.7 | Task Score (%) | 90.7 |
| MEGA-Bench Task - Super CLEVR Scene Understanding | 71.4 | Task Score (%) | 90.6 |
| MEGA-Bench Task - Graph Theory | 42.9 | Task Score (%) | 89.5 |
| MEGA-Bench Task - AV Human Multiview Counting | 26.7 | Task Score (%) | 88.4 |
| MEGA-Bench Task - COCO Object Detection By Query Property | 69.1 | Task Score (%) | 88.4 |
| MEGA-Bench Task - Adapted CVBench Count | 71.4 | Task Score (%) | 87.5 |
Interactive version: theaggregate.ai/model?slug=valley-eagle-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.