Luna Max outperforms Sonnet in DeepSWE at 2.3% of the cost
reach_vb · x · 2026-08-17
On the DeepSWE v1.1 benchmark, GPT-5.6 Luna Max scores 13.3 points higher than Sonnet 5 Max while costing 44x less. DeepSWE evaluates coding agents on 113 original, long-horizon engineering tasks. Luna achieves a 67.2% pass rate at $0.61/task, performing 1.7 points lower than Gemini 3.7 Flash Medium (70% pass rate) but at 70% lower cost.
Related event: GPT-5.6 Luna Max Tops Sonnet 5 Max on DeepSWE at 1/44 the Cost(3 posts)→
More from Models
- AI slide design is even more conspicuous than AI writing — siglesias · 2026-10-03
- Humanlike Qwen3.8-27B LoRA 2.0 Adds Tool Calls, Fooled a Blind Judge 23.5% of the Time — kvyb · 2026-10-03
- Local AI community worries growing dependence on Claude and GPT strengthens closed labs — takoulseum · 2026-10-02
- Unreleased Gemini 4 Argon reportedly matches Claude's best on 3D game generation — 141_1337 · 2026-10-02
- Team ditches GPT-5.4 for GLM in production, sees faster, cheaper, more reliable results — ivan_bezdomny · 2026-10-02
- "Visualize the biggest scam in humanity": Opus 5.5's answer goes viral — zealcaiden · 2026-10-02