BLUEX v2 (Official): leaderboard
BLUEX v2 evaluates open-ended Portuguese university entrance-exam answers. The official full results include 21 models over 880 evaluated subquestions, scored from 0 to 10 by a Sabia-4 rubric judge, with evaluation errors counted as zero. All models receive image captions, including text-only models. The judge also appears among the subjects. This is the full roster of the same experiment whose paper prints only the top and bottom five models; higher is better.
Metric: Mean rubric score (0-10; 880 subquestions; evaluation errors score zero). Source: github.com. Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 21 models tracked. Updated 2 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 9.1 | #99 |
| 2 | GPT-5.4 | 8.92 | #135 |
| 3 | GPT-5 Mini | 8.9 | #359 |
| 4 | Qwen 3.5 122B A10B | 8.83 | #341 |
| 5 | Gemini 3.1 Flash Lite (Preview) | 8.83 | #418 |
| 6 | Qwen 3.5 35B A3B | 8.77 | #490 |
| 7 | Qwen 3.5 27B | 8.74 | #374 |
| 8 | Qwen 3.5 9B | 8.63 | #822 |
| 9 | Sabia-4 | 8.6 | #443 |
| 10 | Gemma 4 26B A4B (IT) | 8.6 | #561 |
| 11 | Sabiazinho-4 | 8.58 | #666 |
| 12 | Qwen 3 14B | 8.57 | #1264 |
| 13 | Qwen 3 30B A3B 2507 Instruct | 8.54 | #1091 |
| 14 | Mistral Small 4 | 8.43 | #1232 |
| 15 | Qwen 3 8B | 8.41 | #1868 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=bluex-v2-official · How It Works · Data refreshed daily, snapshot 2026-11-17.