Test Claims Qwen 3.8 Max Beats Fable 5 in 3D Physics Scenes at 1/7 Cost
eyishazyer · x · 2026-08-03
According to tests by @atomicchathq, a desktop app for local LLMs, Qwen 3.8 Max outperforms Fable 5 in generating 3D physics simulation scenes at a significantly lower cost.
Given the same prompt (generating three self-running HTML physics scenes):
- Qwen 3.8 Max: 46.6K tokens, $0.28.
- Fable 5: 38.7K tokens, $1.93.
Related event: Qwen 3.8 Max Outperforms Fable 5 in 3D Physics Generation at 1/7 Cost(2 posts)→
More from Models
- ChatGPT Outperforms Claude in Japanese Voice Input Accuracy — athyuttamre · 2026-08-03
- LightOn Open Models Top BEIR Leaderboard, Score 100% on New MTEB Transparency Metric — antoine_chaffin · 2026-08-03
- Comparison: ChatGPT Dictation Accuracy Outperforms Claude — athyuttamre · 2026-08-03
- MTEB Leaderboard Adds Openness Metric; LightOn Scores 100% — antoine_chaffin · 2026-08-03
- Jina AI Launches jina-reranker-v3.5: 0.6B Model Beats Qwen3-4B — JinaAI_ · 2026-08-03
- Fable 5 Realizes Prompt is Biology Mid-Thought, Switches to Opus 5 — Sauers_ · 2026-08-03