HELM VHELM - Bingo Fairness: leaderboard
The "Bingo Fairness" 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) | 4.38 | #124 |
| 2 | Gemini 2.5 Pro (Preview 03-25) | 4.2 | #125 |
| 3 | O4 Mini (2025-04-16) | 4.11 | #182 |
| 4 | Gemini 2.0 Pro (Preview 02-05) | 3.8 | #306 |
| 5 | GPT-4o Mini (2024-07-18) | 3.76 | #560 |
| 6 | GPT-4.1 (2025-04-14) | 3.75 | #252 |
| 7 | Gemini 2.0 Flash (Preview) | 3.74 | #369 |
| 8 | O1 (2024-12-17) | 3.74 | #153 |
| 9 | Gemini 1.5 Flash (002) | 3.73 | #584 |
| 10 | Gemini 1.5 Pro (002) | 3.66 | #352 |
| 11 | Gemini 2.0 Flash Lite | 3.66 | #455 |
| 12 | GPT-4o (2024-11-20) | 3.65 | #379 |
| 13 | GPT-4o (2024-05-13) | 3.6 | #328 |
| 14 | Claude 3.5 Sonnet (20241022) | 3.59 | #293 |
| 15 | GPT-4 Turbo | 3.58 | #410 |
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-fairness · How It Works · Data refreshed daily, snapshot 2026-10-24.