VAMPS - Persian: leaderboard
Tool-enabled accuracy on the original Persian versions of the 218 VAMPS (2026) exam questions: the model must plot with Desmos and answer only from the visible graph evidence, thinking disabled. Percent; higher is better.
Metric: Accuracy (%) on the original Persian 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 | 92.7 | #79 |
| 2 | Claude Sonnet 4.6 | 88.5 | #161 |
| 3 | Qwen 3.5 397B A17B (Non-reasoning) | 88.5 | #246 (Qwen 3.5 397B A17B) |
| 4 | Gemini 2.5 Flash (Non-reasoning) | 84.4 | #453 (Gemini 2.5 Flash) |
| 5 | Gemma 4 31B (Non-reasoning) | 84.4 | #394 (Gemma 4 31B) |
| 6 | Qwen 3.5 27B (Non-reasoning) | 82.6 | #359 (Qwen 3.5 27B) |
| 7 | Gemma 4 26B A4B (Non-reasoning) | 81.2 | #615 (Gemma 4 26B A4B) |
| 8 | Qwen 3.5 35B A3B (Non-reasoning) | 76.6 | #482 (Qwen 3.5 35B A3B) |
| 9 | Qwen 3 VL 32B Instruct | 71.6 | #585 |
| 10 | GPT-5.4 (Non-reasoning) | 70.6 | #123 (GPT-5.4) |
| 11 | Ministral 3 14B | 53.2 | #1845 |
| 12 | Ministral 3 8B | 50.5 | #2023 |
| 13 | GPT-4o | 49.5 | #741 |
| 14 | Qwen 3 VL 8B Instruct | 49.1 | #981 |
| 15 | Gemma 3 27B | 46.8 | #1631 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=vamps-persian · How It Works · Data refreshed daily, snapshot 2026-11-13.