Vals Code Migration Leaderboard: Claude Sonnet 5.5 Tops at 86.88%, DeepSeek Costs $1.76
davidbau · x · 2026-10-31
David Bau highlights the refreshed Vals AI Code Migration leaderboard (v1.1, Oct 28, 2026), which tests how accurately and cheaply models can one-shot port programs between languages like COBOL and Java.
- Claude Sonnet 5.5 leads at 86.88% accuracy ($43.88 per test), ahead of Claude Opus 5.5 (81.01%) and GPT-6 Astra (80.58%).
- Value picks: DeepSeek V4.1 Flash 1017 hits 67.52% for just $1.76; MiMo V2.6 Pro scores 48.79% at $0.99; GPT-6.1 Sol delivers 77.32% for $9.51.
- The board covers 19 models from Anthropic, OpenAI, Google, DeepSeek, Alibaba, Meta, Xiaomi, StepFun and more, with cost, token usage and duration per test.
Related event: NetHack Porting Challenge: AI Hits 99.5% Accuracy but Readability Suffers(3 posts)→
More from coding & agent
- LambdaTest's TestMu AI Mapped: From Test Cloud to Agent Verification — Designer_Hair_417 · 2026-10-31
- Open-source ultra-elements: 39 tunable spell VFX in pure three.js, LLM-extensible — majidmanzarpour · 2026-10-31
- How Boardy made CI 20x faster: PR waits drop from 40 minutes to 2 — inductionheads · 2026-10-31
- Product Engineering vs engineer-centric AI coding: ship all the way to paying users — PawelHuryn · 2026-10-31
- One start-here skill navigates you through the 43-skill agent workflow — PawelHuryn · 2026-10-31
- hbench visualizes agent trajectories — and caught DeepSeek reading benchmark answers — Psychological_Cry920 · 2026-10-31