VAMPS: leaderboard
VAMPS (2026) tests visual-assisted mathematical problem solving on 218 Iranian university entrance exam questions where plotting reveals the answer, here in English translation. In this tool-enabled setting the model must obtain one to four Desmos plots and answer only from the graph evidence; the score is accuracy in percent with thinking disabled, higher is better.
Metric: Accuracy (%) on the English versions of the 218 Konkour-seed questions (Iranian university entrance exam algebra and calculus, chosen so that plotting reveals the answer; four-option multiple choice), tool-enabled visual solving: the model must obtain one to four Desmos plots and answer only from the visible graph evidence, no analytical derivation; thinking disabled for every model, temperature 0, answers read from a required JSON block; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 93.6 | #79 |
| 2 | Gemma 4 31B (Non-reasoning) | 89.5 | #394 (Gemma 4 31B) |
| 3 | Claude Sonnet 4.6 | 88.5 | #161 |
| 4 | Qwen 3.5 397B A17B (Non-reasoning) | 88.5 | #246 (Qwen 3.5 397B A17B) |
| 5 | Gemma 4 26B A4B (Non-reasoning) | 85.3 | #615 (Gemma 4 26B A4B) |
| 6 | Qwen 3.5 27B (Non-reasoning) | 83.5 | #359 (Qwen 3.5 27B) |
| 7 | Gemini 2.5 Flash (Non-reasoning) | 78.4 | #453 (Gemini 2.5 Flash) |
| 8 | Qwen 3.5 35B A3B (Non-reasoning) | 76.2 | #482 (Qwen 3.5 35B A3B) |
| 9 | Qwen 3 VL 32B Instruct | 74.3 | #585 |
| 10 | GPT-5.4 (Non-reasoning) | 66.5 | #123 (GPT-5.4) |
| 11 | Ministral 3 14B | 59.6 | #1845 |
| 12 | Ministral 3 8B | 58.7 | #2023 |
| 13 | Gemma 3 27B | 50.5 | #1631 |
| 14 | Qwen 3 VL 8B Instruct | 50 | #981 |
| 15 | GPT-4o | 49.5 | #741 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=vamps · How It Works · Data refreshed daily, snapshot 2026-11-13.