CountBench
Progress Over Time
Interactive timeline showing model performance evolution on CountBench
State-of-the-art frontier
Open
Proprietary
CountBench Leaderboard
9 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  ByteDance | — | 256K | $0.25 / $2.00 | ||
| 2 |  Alibaba Cloud / Qwen Team | 27B | 262K | $0.26 / $2.60 | ||
| 2 | Alibaba Cloud / Qwen Team | 35B | 262K | $0.14 / $1.00 | ||
| 2 | Alibaba Cloud / Qwen Team | 28B | 262K | $0.32 / $3.20 | ||
| 5 | Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 6 | Alibaba Cloud / Qwen Team | 122B | 262K | $0.29 / $2.40 | ||
| 7 | ByteDance | — | 256K | $0.10 / $0.40 | ||
| 8 | Alibaba Cloud / Qwen Team | 236B | — | — | ||
| 9 | 2B | — | — |
Notice missing or incorrect data?
What is CountBench?
CountBench evaluates object counting capabilities in visual understanding.
CountBench is a image benchmark evaluating models on reasoning, spatial reasoning, and vision tasks. LLM Stats tracks 9 models on this benchmark, scored on a 0–100 scale. The current average is 11.5, with the leader at 96.3.
Compare leaders on the best AI for reasoning, best AI for spatial reasoning and best AI for vision leaderboards.
Current leaders
Seed 1.8 from ByteDance currently leads the CountBench leaderboard with a score of 96.300 across 9 evaluated AI models.
FAQ
Common questions about the CountBench benchmark and leaderboard.