Verified65% confidenceBenchmarkExact time

Qwen3-4B is already on par with DeepSeek V3 or GPT-4o on multiple reasoning evaluation metrics.

3

Sources

65%

Confidence

Medium-term (~90 days)

Relevance

7/21/2026

First Seen

Valid until: 10/19/2026

Sources

Qwen3 Deep Dive: A Complete Look at the Open-Source Hybrid Reasoning Model

Related Claims

VerifiedQwen3.5's parameter activation rate is 4.3%, while DeepSeek V3's 671B model has an activation rate of 5.5%.79% similar UnverifiedLlama 3.1 405B's score on MMLU is already close to the level of GPT-4o, and Qwen 2.5 72B has surpassed GPT-4 Turbo on certain metrics in math and code generation benchmarks.76% similar UnverifiedQwen3-1.7B's overall causal faithfulness is only 54.8%, far below that of Qwen3-4B.75% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/583666

API

curl https://kongchang.com/api/v1/knowledge/claims/583666

MCP

get_claim(id=583666)