Expired50% confidenceBenchmarkExact time
On the DeepSWE coding leaderboard, Beam scored 44.4 points, ranking last, below DeepSeek V4.1 Flash's 74.2 points, Kimi K3's approximately 68 points, GLM's approximately 61 points, and Qwen3 Max's approximately 51 points.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/8/2026
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 Entities
Related Claims
UnverifiedDeepSeek-V4-Flash-Vision-Exp adopts a MoE architecture with approximately 305B total parameters, activating only approximately 13B per token, for an activation rate of approximately 4.6%.72% similarPartially VerifiedOn a dual-Spark system, DeepSeek V4 Flash (FP8 quantization) peaks at approximately 53 tokens per second.70% similarUnverifiedThe Qwen3 Max version adopts a MoE architecture with approximately 2.4 trillion parameters, roughly 4 times that of DeepSeek 671B.70% similarUnverifiedThe UD-Q8_K_XL quantized version of DeepSeek V4 Flash has a file size of 162 GB, uses MXFP4+BF16 mixed precision, and achieves completely lossless quality.70% similarUnverifiedDeepSeek, Qwen, and GLM have each released a high-speed, lightweight Flash version alongside their flagship models, and the Flash versions generally have higher download counts.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987290API
curl https://kongchang.com/api/v1/knowledge/claims/987290MCP
get_claim(id=987290)