Gemini-Exp-1206: benchmark results
Provider: Google. Released 2024-12-06. Access: API.
Aggregate Rating 1663 ± 17, rank #534 of 10916 rated models, from 549 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MEGA-Bench - Application: Coding | 57.9 | Average Score (%) | 100 |
| MEGA-Bench Task - Animal Pose Estimation | 38.9 | Task Score (%) | 100 |
| MEGA-Bench Task - App Interactive Operations Word | 78.6 | Task Score (%) | 100 |
| MEGA-Bench Task - App Interactive Operations iPhone Settings | 100 | Task Score (%) | 100 |
| MEGA-Bench Task - App Layout Understanding Word | 71.4 | Task Score (%) | 100 |
| MEGA-Bench Task - App Layout Understanding iPhone Settings | 100 | Task Score (%) | 100 |
| MEGA-Bench Task - Autorater Artifact Reason | 93.3 | Task Score (%) | 100 |
| MEGA-Bench Task - Autorater Unmask | 78.6 | Task Score (%) | 100 |
| MEGA-Bench Task - Chinese Idiom Recognition | 100 | Task Score (%) | 100 |
| MEGA-Bench Task - Code Programming Test Advanced | 63 | Task Score (%) | 100 |
| MEGA-Bench Task - Code Programming Test Easy | 59 | Task Score (%) | 100 |
| MEGA-Bench Task - Code Translation Advanced | 35.7 | Task Score (%) | 100 |
Interactive version: theaggregate.ai/model?slug=gemini-exp-1206 · How It Works · Data refreshed daily, snapshot 2026-11-08.