NEXT-EVAL
Harbor: pendingEffective evaluation of web data record extraction methods is crucial, yet hampered by static, domain-specific benchmarks and opaque scoring practices.
- Samples
- N/A
- Released
- 2025
- Scores
- 0
NExT-QA
NExT-QA is a VideoQA benchmark targeting the explanation of video contents.
How to run
ltb · next-qa
$ npm i -g lettokenburn-cli$ ltb bench info next-qa
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
9 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| InternVL-2.5 | 85.5 | N/A | Independent | medium | Dec 6, 2024 | arxiv.org |
| LLaVA-Video | 83.2 | N/A | Independent | medium | Oct 3, 2024 | arxiv.org |
| Qwen2-VL | 81.2 | N/A | Independent | medium | Sep 18, 2024 | arxiv.org |
| LLaVA-OV | 80.2 | N/A | Independent | medium | Aug 6, 2024 | arxiv.org |
| LLaVA-NeXT-Interleave | 79.1 | N/A | Independent | medium | Jul 10, 2024 | arxiv.org |
| LLaMA-VQA | 75.5 | N/A | Independent | medium | Oct 24, 2023 | arxiv.org |
| Mistral | 51.1 | N/A | Independent | medium | Oct 10, 2023 | arxiv.org |
| Gemini Ultra | 29.9 | N/A | Independent | medium | Dec 19, 2023 | arxiv.org |
| Gemini Pro | 28.0 | N/A | Independent | medium | Dec 19, 2023 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
NExT-QA is a VideoQA benchmark targeting the explanation of video contents. It challenges QA models to reason about the causal and temporal actions and understand the rich object interactions in daily activities, e.g., "why is the boy crying?" and "How does the lady react after the boy fall backward?". It supports both multi-choice and generative open-ended QA tasks. The videos are untrimmed and the questions usually invoke local video contents for answers.