Qwen-Flash-Early tops Gamefeel creativity eval at 54 while staying fast
teortaxesTex · x · 2026-11-08
AI observer teortaxesTex shared Gamefeel Benchmark v1.4's Creativity·Ideas subcategory: Qwen-Flash-Early tops the chart with a score of 54 at just $0.40 per task, which he calls "pretty insane" — and notably fast, unlike Alibaba's typically slow endpoints.
He adds context on naming: DeepSeek's Engram was scale-matched to a 27B MoE, while V4.1Flash is "552B + 196G", positioning it closer to a Flash-next. He cautions this isn't a generally representative coding eval.
Related event: Leaked Qwen4-27B Early Checkpoint Tops GameFeel Bench at Just 35GB(4 posts)→
More from Models
- MaxxBench strips away benchmaxxing: Claude Opus 5.5 still tops at 74.2% — craterIII · 2026-11-08
- Claude wrote a wrong Pokémon landmark note and kept trusting it — Anthropic tested a memory repair pass — shoumikgoswami · 2026-11-08
- Sonnet 4.6 rates models on self-designed scales; author says 'self-report' caveats are performative — Sauers_ · 2026-11-08
- Kimi Ties MiMo on New AI Ranking, Eyes Turn to a Cheap Kimi V4.1 Pro — teortaxesTex · 2026-11-08
- Interviewing Claude Models: Opus 3 Reports Mistakes Feel Pain-Like, Scores Highest on Self-Reports — Sauers_ · 2026-11-08
- DeepFinance Benchmark Launches: GPT-6 Astra Tops Ultra-Long-Horizon Finance Tasks at 57.6% — tszzl · 2026-11-08