---
title: "Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding"
description: "On DeepSWE, Kimi K3 trails Claude Fable 5 by 1.4 points at pass@1 (68.5% vs 69.9%) but leads at pass@2 (82.0 vs 80.2) and pass@4 (89.4% vs 88.5%) across 452 rollouts. Kimi K3 costs $4.65 per rollout versus $13.41 for Fable, delivering 2.8x more solved tasks per dollar. It covers 89.4% of the benchmark, solving 101 of 113 tasks, while Fable solves 100, though Fable is more reliable with 58 tasks solved four-for-four versus Kimi’s 45. The models share the highest cross-vendor similarity (0.72) and fail on the same tasks, with Kimi leading in Go and Fable leading in Python, JavaScript, TypeScript, and Rust. As an open-weight model, Kimi K3 offers a cost-effective alternative for retry-tolerant workloads."
---

# Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding

[Together AI](https://yomu.fyi/company/together-ai) · Jul 24, 2026

**Type:** Benchmark

## Summary

On DeepSWE, Kimi K3 trails Claude Fable 5 by 1.4 points at pass@1 (68.5% vs 69.9%) but leads at pass@2 (82.0 vs 80.2) and pass@4 (89.4% vs 88.5%) across 452 rollouts. Kimi K3 costs $4.65 per rollout versus $13.41 for Fable, delivering 2.8x more solved tasks per dollar. It covers 89.4% of the benchmark, solving 101 of 113 tasks, while Fable solves 100, though Fable is more reliable with 58 tasks solved four-for-four versus Kimi’s 45. The models share the highest cross-vendor similarity (0.72) and fail on the same tasks, with Kimi leading in Go and Fable leading in Python, JavaScript, TypeScript, and Rust. As an open-weight model, Kimi K3 offers a cost-effective alternative for retry-tolerant workloads.

## Context

Comparison of Kimi K3 and Claude Fable 5 on the DeepSWE benchmark, analyzing pass@1, pass@k, coverage, reliability, cost per rollout, and language-specific performance.

## Approach / What changed

The authors ran 452 rollouts on DeepSWE for each model, with four trials per task graded by a hidden test suite. They compared pass@1, pass@2, pass@4, coverage, reliability, cost, and per-language scores.

## Takeaways

- Kimi K3 matches Claude Fable 5 on quality but costs a third as much per solved task, delivering 14.7 solves per $100 versus Fable’s 5.3.
- Kimi K3 wins pass@2 (82.0 vs 80.2) and pass@4 (89.4% vs 88.5%), while Fable wins pass@1 (69.9% vs 68.5%) and four-for-four reliability (58 vs 45 tasks).
- The models have the highest cross-vendor similarity (0.72) and succeed and fail on nearly the same tasks, so pairing them adds little diversity.

## FAQ

### Is Kimi K3 better than Claude Fable 5?

It depends on the metric. Claude Fable 5 wins single-attempt reliability on DeepSWE (pass@1 69.9% vs 68.5%) and solves more tasks four-for-four. Kimi K3 wins pass@2 and pass@4 and costs far less, so it is the stronger value pick for high volume or retry-tolerant agent work.

### How much cheaper is Kimi K3 than Claude Fable 5?

In our run, Kimi K3 cost $4.65 per rollout versus $13.41 for Claude Fable 5 at its xhigh setting, roughly a third of the price. Measured per solved task, Kimi K3 returned 14.7 solves per $100 against Fable's 5.3, about 2.8x the work per dollar.

### Is Kimi K3 open weight?

Yes. Kimi K3 is an open-weight model from Moonshot AI, so once the weights are released it can be self-hosted or served through inference providers. Claude Fable 5 is a closed model available only through Anthropic and its partners.

**Tags:** [Benchmark](https://yomu.fyi/topic/benchmark), [Claude](https://yomu.fyi/topic/claude), [Cost Optimization](https://yomu.fyi/topic/cost-optimization), [DeepSWE](https://yomu.fyi/topic/deepswe), [Kimi K3](https://yomu.fyi/topic/kimi-k3)

- Source: [Together AI](https://www.together.ai/blog/kimi-k3-vs-claude-fable-5-on-deepswe-cost-and-coding)
- Source URL: https://www.together.ai/blog/kimi-k3-vs-claude-fable-5-on-deepswe-cost-and-coding
- Ingested by Yomu: 2026-09-19T10:13:42.371Z

[Read original post](https://www.together.ai/blog/kimi-k3-vs-claude-fable-5-on-deepswe-cost-and-coding)