AlgoPuzzleVQA
Harbor: pendingWe introduce the novel task of multimodal puzzle solving, framed within the context of visual question-answering.
- Samples
- 1,800
- Released
- 2024
- Scores
- 1
$ npm i -g lettokenburn-cli$ ltb bench pull chartqa --n 50$ ltb bench run ./chartqa -a claude-code -m anthropic/claude-opus-4-8$ ltb bench push
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| Gemini Ultra | 80.8 | N/A | Independent | medium | Dec 19, 2023 | arxiv.org |
| Qwen-VL-Max | 66.3 | N/A | Independent | medium | Aug 24, 2023 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
ChartQA (Chart QA) — 图表理解问答. Scoring: 准确率. Difficulty: 中. Imported from benchmark_research.md (2026-06).