CountBench (CountBench)

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

Top Models on CountBench — March 2026

As of March 2026, Qwen3.6 Plus leads the CountBench leaderboard with 97.6% , followed by Gemini 3 Pro (97.3%) and Qwen3.5 397B (97.2%).

6 modelsMultimodal & GroundedCurrentDisplay onlyUpdated April 2, 2026

According to BenchLM.ai, Qwen3.6 Plus leads the CountBench benchmark with a score of 97.6%, followed by Gemini 3 Pro (97.3%) and Qwen3.5 397B (97.2%). The top models are clustered within 0.4 points, suggesting this benchmark is nearing saturation for frontier models.

6 models have been evaluated on CountBench. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. CountBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

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.

Qwen3.6 launch benchmarks

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.

Leaderboard (6 models)

#1Qwen3.6 Plus
97.6%
#2Gemini 3 Pro
97.3%
#3Qwen3.5 397B
97.2%
#4Kimi K2.5
94.1%
#5GPT-5.2
91.9%
#6Claude Opus 4.5
90.6%

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 Plus by Alibaba currently leads with a score of 97.6% on CountBench.

How many models are evaluated on CountBench?

6 AI models have been evaluated on CountBench on BenchLM.

Last updated: April 2, 2026 · BenchLM version CountBench 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.