Expired50% confidenceBenchmarkExact time
On 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.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/23/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/21/2026(expired)
Sources
Related Claims
UnverifiedThe 3D watch problem is the hardest question in KingBench, with the highest score being 4 points achieved by Fable 5; Qwen 3.8 Max scored 3 points.77% similarUnverifiedQwen 3 Max achieved a perfect score of 10 in difficult math problems, an archery simulation game, and long-horizon agent tasks.75% similarUnverifiedQwen 3 Max answered a difficult math problem (an ordered pair arrangement counting question with the correct answer of 2460) completely correctly, placing it in the same tier as Claude, Kimi K3, and GPT-5.72% similarUnverifiedIn the reviewer's Ping benchmark test, Qwen 3 Max scored 8 points on the 3D contact lens modeling question, making it the second-best model the reviewer had tested (previously only the Claude flagship had achieved a perfect score, while Opus scored only 7).69% similarPartially VerifiedBoth Qwen 3 Max and DeepSeek-V3 adopt the MoE architecture with total parameter counts reaching hundreds of billions, but the parameters actually activated during inference are only a small fraction of the total.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/601755API
curl https://kongchang.com/api/v1/knowledge/claims/601755MCP
get_claim(id=601755)