Skip to main content

Benchmark profile

CountBench

A visual counting benchmark that tests whether a model can count objects and entities reliably in complex scenes.

Data verified

Benchmark score on CountBench — July 23, 2026

BenchLM mirrors the published score view for CountBench. Qwen3.6-27B leads the public snapshot at 97.8% , followed by LFM2.5-VL-450M (73.3%). BenchLM does not use these results to rank models overall.

2 modelsMultimodal & GroundedCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (2 models)

Score
1
Qwen3.6-27BAlibaba · Open weight
97.8%
2
LFM2.5-VL-450MLiquidAI · Open weight
73.3%

About CountBench

Year

2026

Tasks

Visual counting tasks

Format

Image-grounded counting

Difficulty

Fine-grained visual perception

Counting failures are a common multimodal weakness even in otherwise strong models. CountBench isolates that skill and makes it easy to compare raw perception accuracy across models.

BenchLM freshness & provenance

Version

CountBench 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does CountBench measure?

A visual counting benchmark that tests whether a model can count objects and entities reliably in complex scenes.

Which model scores highest on CountBench?

Qwen3.6-27B by Alibaba currently leads with a score of 97.8% on CountBench.

How many models are evaluated on CountBench?

2 AI models have been evaluated on CountBench on BenchLM.

Compare Top Models on CountBench

Last updated: July 23, 2026 · BenchLM version CountBench 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.