vLLM @vllm_project · 29 Aug 2026
GLM-5.3-Flash is live on Fireworks on day… 2 Why? Because we take quality very seriously. We found a benchmark discrepancy we couldn’t explain, so we delayed the launch to investigate. Day 0 (Wed): we saw 2x longer thinking on reasoning-heavy benchmarks (AIME & GPQA) for open https://t.co/6MuHYV2XHn
86 631Views
448Likes
21Reposts
28Replies
8Quotes
0Bookmarks
Is that a lot?
3.34×vs this author's median25 968 views is typical
67Percentile for this authorof 6 recent posts
29.9×vs 10K–100K median2 896 views is typical
179.14%Reachviews ÷ followers
0.58%Engagement rateof viewers reacted