Expired85% confidenceFactTime unknown
On code-related tasks such as LiveBench, QwQ-32B surpasses DeepSeek R1 by approximately two percentage points.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedQwQ-32B performs nearly on par with the full version of DeepSeek R1 across multiple mainstream benchmarks, and surpasses it on some tasks.76% similarUnverifiedDeepSeek V4 Pro achieved a score of 3206 on CodeForces and a pass rate of 95.2% on the MMT-266 benchmark.69% similarVerifiedDeepSeek-V3 has 671B total parameters, but only approximately 37B parameters are activated per inference.62% similarUnverifiedBenchmark tests show that Qwen3-235B's performance matches or even surpasses DeepSeek R1, with advantages in categories such as math, coding, and reasoning.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/23193API
curl https://kongchang.com/api/v1/knowledge/claims/23193MCP
get_claim(id=23193)