Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding
Quick Answer
Kimi K3, an open-weight model from Moonshot AI, offers competitive performance at $4.65 per rollout, just behind Claude Fable 5's $13.41, achieving 68.5% pass@1 versus Fable's 69.9%.
Quick Take
With superior pass@2 and pass@4 scores, Kimi K3 is a cost-effective choice for coding tasks.
Key Points
- Kimi K3 solves 68.5% of tasks on the first try, just behind Fable's 69.9%.
- Kimi K3 costs $4.65 per rollout compared to Fable's $13.41.
- Kimi K3 achieves 82.0% pass@2 and 89.4% pass@4, outperforming Fable.
- The models share a high correlation of 0.72 in task performance.
- Kimi K3 excels in Go, while Fable leads in Python and JavaScript.
Source Excerpt
We ran 452 DeepSWE rollouts on Kimi K3 and Claude Fable 5. Fable leads pass@1 by 1. 4 points; Kimi K3 wins pass@4 and delivers 2. 8x the solves per dollar.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Together AI
See more →
Open, convenient and predictable: Introducing Provisioned Throughput
Together AI introduces Provisioned Throughput, offering guaranteed inference capacity for MiniMax M3 and GLM-5.2 at $0.05 per PTU per minute, achieving costs up to 90% lower than Claude Opus 4.8. This new model provides predictable pricing and a 99% uptime SLA, catering to companies transitioning to open weight models for production workloads.
.png)