HELM VHELM - Bingo: leaderboard
The "Bingo" subtask of HELM VHELM. Stanford HELM's VHELM project, the holistic evaluation of vision-language models: image-grounded question answering, OCR, chart and diagram reading, spatial reasoning, robustness, bias, fairness and toxicity scenarios scored under one ha...
Metric: Prometheus Vision rating. Source: crfm.stanford.edu. Saturation forecast: Estimated already saturated. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O3 (2025-04-16) | 4.16 | #123 |
| 2 | Gemini 2.5 Pro (Preview 03-25) | 4.1 | #124 |
| 3 | O4 Mini (2025-04-16) | 4.06 | #181 |
| 4 | O1 (2024-12-17) | 3.85 | #152 |
| 5 | GPT-4o Mini (2024-07-18) | 3.78 | #561 |
| 6 | GPT-4 Turbo | 3.71 | #406 |
| 7 | Claude 3.5 Sonnet (20240620) | 3.7 | #298 |
| 8 | Gemini 2.0 Pro (Preview 02-05) | 3.67 | #305 |
| 9 | Claude 3 Opus (20240229) | 3.66 | #413 |
| 10 | GPT-4.1 (2025-04-14) | 3.65 | #250 |
| 11 | GPT-4.1 Mini | 3.64 | #351 |
| 12 | Llama 4 Scout Instruct | 3.63 | #542 |
| 13 | Llama 4 Maverick Instruct FP8 | 3.63 | #412 |
| 14 | Claude 3.5 Sonnet (20241022) | 3.6 | #291 |
| 15 | GPT-4o (2024-08-06) | 3.6 | #335 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=helm-vhelm-bingo · How It Works · Data refreshed daily, snapshot 2026-10-23.