Moonshot's Kimi K3 outperforms Fable 5 in frontend code but lags far behind in complex math
Quick Answer
Moonshot's Kimi K3 excels in frontend code with a score of 1,679, surpassing Fable 5's 1,631, marking a first for Chinese models.
Quick Take
However, it struggles in complex math, achieving only 39% accuracy on FrontierMath Tier 4, while competitors like OpenAI and Anthropic reach close to 90%.
Key Points
- Kimi K3 scores 1,679 in frontend benchmarks, leading the field.
- Fable 5 scores 1,631, trailing Kimi K3 in human preference ratings.
- Kimi K3 only achieves 39% accuracy on the hardest math tasks.
- Top Western models score around 90% on similar complex math benchmarks.
- This performance highlights disparities in AI capabilities across regions.
Source Excerpt
From the original publisher, up to about 700 charactersMoonshot's Kimi K3 is the first Chinese model to top the Code Arena: Frontend rankings, beating Claude Fable 5 and GPT-5. 6 Sol by a wide margin. But on advanced math, the gap is stark: Kimi K3 scores only about 39 percent on FrontierMath Tier 4, while models from OpenAI and Anthropic hit close to 90.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
