Expired75% confidenceFactTime unknown
In free model testing, MiniMax performed adequately, Qwen 3 had bugs, and DeepSeek failed completely.
1
Sources
75%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedIn the Super Mario game generation test, MiniMax M3 outperformed DeepSeek and other models.70% similarVerifiedDeepSeek released the V3.2 model, which matches Gemini 3.0 Pro on multiple benchmarks68% similarUnverifiedDeepSeek uses NVIDIA cards on V3 but not the official software libraries, writing operators at the kernel level using TileLang, with an efficiency loss of approximately 1% to 2%.65% similarUnverifiedIn testing, DeepSeek V4 Pro completed the basic functions normally, but had a dropdown style issue: only 3 of the 5 languages were visible and could not be scrolled through.65% similarVerifiedUnsloth supports fine-tuning mainstream open-source large models including Gemma 4, Qwen3, DeepSeek, and gpt-oss.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/14362API
curl https://kongchang.com/api/v1/knowledge/claims/14362MCP
get_claim(id=14362)