# WorldVQA ForceAnswer leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-world-vqa-force-answer

Every model the catalog carries a published WorldVQA ForceAnswer value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Forced-answer visual QA |
| Tasks | Atomic visual world-knowledge questions |
| Difficulty | Fine-grained visual knowledge |
| Published by | [Kimi K3: Open Frontier Intelligence](https://www.kimi.com/blog/kimi-k3) |

A forced-answer WorldVQA variant for atomic visual world knowledge.

## WorldVQA ForceAnswer ranking

1 model with a published WorldVQA ForceAnswer value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Forced-answer visual QA | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 51.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
