A visual counting benchmark that tests whether a model can count objects and entities reliably in complex scenes.
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%).
Qwen3.6 Plus
Alibaba
Gemini 3 Pro
Qwen3.5 397B
Alibaba
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.
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 benchmarksVersion
CountBench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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.
A visual counting benchmark that tests whether a model can count objects and entities reliably in complex scenes.
Qwen3.6 Plus by Alibaba currently leads with a score of 97.6% on CountBench.
6 AI models have been evaluated on CountBench on BenchLM.
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.