Qwen3.8 Max Enters Frontier Tier, Splitting Leaderboard Against GPT and Fable
Scobleizer · x · 2026-08-03
According to newly shared benchmark data, Qwen3.8 Max did not cleanly beat every frontier model, but it successfully split the leaderboard, marking its entry into the top tier of LLMs with no obvious weaknesses.
Key comparisons:
- PaperBench: 93.0 vs. GPT-5.6 Sol at 90.5
- OSWorld-Verified: 86.1 vs. Fable 5 at 85.0
- IFBench: 82.8 vs. GPT-5.6 Sol at 72.7
- Dense200: 87.0 vs. Gemini 3.1 Pro at 69.7
Fable 5 still dominates SWE-Pro and FrontierSWE, while GPT leads in TerminalBench and GPQA. The results show Qwen has firmly arrived at the frontier level.
Related event: Qwen3.8-Max Ranks Top Tier Across Benchmarks, Open-Source Narrows Gap(7 posts)→
More from Models
- Ornith-1.5 Open Models Released, Claiming Claude Opus Performance — alejandroll10 · 2026-08-26
- 14-year AI veteran: Grok understood code I thought no one ever would — Kuprel · 2026-08-26
- Together Ranks Top Open Models: Kimi K3 and DeepSeek V4 Lead Use Cases — togethercompute · 2026-08-26
- Questions over Astra's progress: 2 months for 3 more models? — teortaxesTex · 2026-08-26
- View: Tokens-per-second matters more than model size now — natesiggard · 2026-08-26
- Tiel-Coder-35B achieves 121.4 tok/s for local inference — DerTomsn · 2026-08-26