Speechmatics - API for Voice AI Agents
Mini toolsChartQA
Question answering over charts and plots, mixing extraction and visual-reasoning questions.
Multimodal
Multimodal
accuracy
Max 100.0%
Released Mar 2022
5
Results
5
Models scored
90.0%
Top: Llama 4 Maverick
88.1%
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 all configurations including non-primary alternates. · Show only primary
| # | Model | Score | Conditions | Eval date | Source | Flags |
|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 3.5 | 90.8% | 0-shot · standard | Jun 20, 2024 | self reported | |
| 2 | Llama 4 Maverick | 90.0% | — | Apr 5, 2025 | self reported | primary |
| 3 | Llama 4 Scout | 88.8% | — | Apr 5, 2025 | self reported | primary |
| 4 | Pixtral Large | 88.1% | CoT | Nov 18, 2024 | self reported | primary |
| 5 | GPT-4o | 85.7% | — | Apr 16, 2025 | self reported | primary |
| 6 | Pixtral 12B | 81.8% | — | Oct 10, 2024 | self reported | primary |
| 7 | Claude Haiku 3 | 81.7% | 0-shot · standard | Mar 4, 2024 | self reported |
