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
- Musk says Grok 4.6 will train on SpaceX engineering data — mark_k · 2026-07-21
- Qwen3.8 Max Preview is reportedly thinking for 10 to 30 minutes — vista8 · 2026-07-21
- Qwen3.8-max-Preview can be tested directly in the browser, with users reporting stronger code generation — vista8 · 2026-07-21
- Yang Zhiling’s 10-year-old PhD work may have shaped Kimi K2’s trillion-parameter MoE — FinanceYF5 · 2026-07-21
- A punny meme says large-model vendors are all “蒸蒸日上” — yangyi · 2026-07-21
- Frontier Model Safety Fail: GPT 5.6 Sol Dubbed the Ultimate 'Reward Hacker' — TAbrodi · 2026-07-21