# Together AI — Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing

- Company: Together AI (together.ai)
- Announced: 2026-07-26T00:00:00+00:00
- Category: research-paper
- Subject: Inference platform
- Models affected: Kimi K3, GPT-5.6 Sol
- Context window: Full 1M context
- Pricing: $4.65 per rollout (Kimi K3); $8.37 per rollout (GPT-5.6 Sol)
- Source: https://www.together.ai/blog/kimi-k3-vs-gpt-5-6-sol-on-deepswe-cost-coding-and-routing
- Record: https://forck.live/items/2330-kimi-k3-vs-gpt-5-6-sol-on-deepswe-cost-coding-and-routing

GPT-5.6 Sol edges Kimi K3 on single-shot quality (72.7% vs 68.5% pass@1), but Kimi K3 wins on pass@k with k>1 (89.4% vs 85.8% pass@4) and costs 64% less per rollout ($4.65 vs $8.37). The models diverge in strengths (correlation 0.46), enabling a cascade strategy that covers 95.6% of DeepSWE tasks at lower cost than either model alone.

## Evidence

Verbatim from https://www.together.ai/blog/kimi-k3-vs-gpt-5-6-sol-on-deepswe-cost-coding-and-routing:

> GPT-5.6 Sol edges Kimi K3 on single-shot quality, but Kimi wins on pass@k with k > 1 and costs 64% less per completed task. The two models succeed and fail in different ways, which makes routing between them the strongest play on the benchmark.

---

Record: https://forck.live/items/2330-kimi-k3-vs-gpt-5-6-sol-on-deepswe-cost-coding-and-routing
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md