Benchmark
SimpleVQA Benchmark
What is SimpleVQA?
SimpleVQA is a visual question answering benchmark focused on simple queries. Benchmark Radar tracks 14 reported scores for SimpleVQA, cited by 1 source…
- Modality
- multimodal
- Evaluates
- multimodal, image to text, general, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 14
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/simplevqa?top_n=500
SimpleVQA results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5V-Turbo | Z.ai | 0.782 | 2026-04-02 | evidence |
| Kimi K2.5 | Moonshot AI | 0.712 | 2026-01-27 | evidence |
| LFM2.5-VL-3B | Liquid AI | 0.354 | 2026-08-12 | evidence |
| Muse Spark | Meta | 0.713 | 2026-04-08 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.613 | 2025-09-22 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.617 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.56 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.583 | 2026-02-24 | evidence |
| Qwen3.6 Plus | Qwen | 0.673 | 2026-04-02 | evidence |
| Qwen3.6-27B | Qwen | 0.561 | 2026-04-21 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.589 | 2026-04-16 | evidence |
| Qwen3.7-Plus | Qwen | 0.817 | 2026-05-31 | evidence |
| Seed 2.1 Pro | ByteDance | 0.745 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.711 | 2026-06-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.