Expired50% confidenceBenchmarkExact time
Qwen 3 Max achieved a perfect score of 10 in difficult math problems, an archery simulation game, and long-horizon agent tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/24/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/22/2026(expired)
Sources
Related Claims
UnverifiedQwen 3 Max scored a perfect 10 points on long-horizon agent tasks (building a panda dataset, fine-tuning Gemma 2B, and setting up a local web interface).75% similarUnverifiedOn the most difficult 3D watch task, Qwen 3 Max scored only 3 points and did not fully implement all features, though the highest score on that task was 4 points by the Claude flagship.75% similarUnverifiedQwen3.7 Max maintains a leading position on high-cognitive-intensity tasks such as mathematical reasoning and logical analysis74% similarUnverifiedQwen3.7 Max surpassed the Claude series models and the previous generation Qwen3.6 in general agent capability evaluations.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/604002API
curl https://kongchang.com/api/v1/knowledge/claims/604002MCP
get_claim(id=604002)