Wispr Flow - Don’t type, just speak
Mini toolsMathVista
MathVista (testmini)
Mathematical reasoning over visual contexts: figures, charts, diagrams, geometric drawings.
Multimodal
Multimodal
Accuracy
Max 100.0%
Released Oct 2023
9
Results
9
Models scored
87.4%
Top: Qwen 3.6 27B
72.0%
Median
Best results
Top primary scores; one row per model.
Frontier over time
Each dot is one model result; the line traces the running best score.
All results
Showing one canonical row per model. Show all configurations
| # | Model | Score | Conditions | Eval date | Source | Flags |
|---|---|---|---|---|---|---|
| 1 | Qwen 3.6 27B | 87.4% | 0-shot · standard | — | Self-reported | Primary |
| 2 | o3 | 86.8% | — | 16 Apr 2025 | Self-reported | Primary |
| 3 | o4 mini | 84.3% | — | 16 Apr 2025 | Self-reported | Primary |
| 4 | Llama 4 Maverick | 73.7% | — | 05 Apr 2025 | Self-reported | Primary |
| 5 | GPT 4.1 | 72.0% | — | 14 Apr 2025 | Self-reported | Primary |
| 6 | o1 | 71.8% | — | 16 Apr 2025 | Self-reported | Primary |
| 7 | Llama 4 Scout | 70.7% | — | 05 Apr 2025 | Self-reported | Primary |
| 8 | GPT-4o | 63.8% | — | 16 Apr 2025 | Self-reported | Primary |
| 9 | Pixtral 12B | 58.3% | CoT | 10 Oct 2024 | Self-reported | Primary |
