Kimi K3 Lags Behind Muse Spark in Evaluation
adonis_singh · x · 2026-07-17
In the eyebench test, muse-spark-1.1 performed exceptionally well, essentially outperforming other models except for gpt-5.4/5.6.
The author pointed out that kimi-k3 scored about 4 points lower than muse, and its testing cost was roughly 10 times higher over 100 questions, making the results "not look great."
Related event: Kimi K3 Lags Behind Muse Spark in Benchmarks with Higher Costs(2 posts)→
More from Models
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11
- Terminal Bench v4: GLM-5.3 Leads at 41.9%, Kimi-K3 Underwhelms at 12.6% — Ok_Warning2146 · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11