Code Migration leaderboard
Rewriting working programs in a new language, graded on whether the new program still passes its tests. Claude Sonnet 5.5 leads with 86.88%.
- Models
- 27
- Leader
- Claude Sonnet 5.5
- Source
- Vals AI
- As of
- Oct 24, 2026
Open weightsProprietaryBest for the price
Full leaderboard
| Rank | Model | Lab | Accuracy | Cost / test | Harness | Price in / out |
|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 5.5 | Anthropic | 86.88% | $43.88 | — | $2 / $10 |
| 2 | Claude Opus 5.5 | Anthropic | 81.01% | $72.40 | — | $4 / $20 |
| 3 | GPT-6 Astra | OpenAI | 80.58% | $62.07 | — | $10 / $50 |
| 4 | GPT-6.1 Sol | OpenAI | 77.32% | $9.51 | — | $2 / $10 |
| 5 | Muse Wonder | Meta | 72.36% | $47.93 | — | $4 / $20 |
| 6 | Gemini 4 Argon | 70.80% | $44.79 | — | $2 / $10 | |
| 8 | Muse Wonder Full | Meta | 62.79% | $23.58 | — | — |
| 9 | DeepSeek-V4.1-Flash-20260910 | DeepSeek | 58.94% | $1.09 | — | $0.15 / $0.60 |
| 10 | Qwen3.8-Max | Alibaba | 57.19% | $27.08 | — | $2 / $6 |
| 11 | GLM-5.3 | Z.ai | 55.07% | $34.91 | — | $0.079 / $1.40 |
| 12 | Grok 4.7 | xAI | 53.22% | $38.05 | — | $2 / $6 |
| 13 | Claude Haiku 5.5 | Anthropic | 52.36% | $6.20 | — | $0.10 / $0.50 |
| 14 | DeepSeek-V4-Pro | DeepSeek | 51.99% | $12.16 | — | $0.66 / $1.98 |
| 15 | GLM-5.3-Flash | Z.ai | 51.65% | $4.48 | — | $0.15 / $0.50 |
| 16 | MiMo-V2.6-Pro | Xiaomi | 48.79% | $0.99 | — | $0.43 / $0.87 |
| 17 | Step 5 Preview | StepFun | 47.00% | $8.61 | — | $1 / $2.70 |
| 18 | GPT-6 Luna | OpenAI | 46.67% | $0.83 | — | $0.10 / $0.50 |
| 19 | Hy4 preview | Tencent | 45.36% | $3.58 | — | $0.75 / $2.25 |
| 20 | MiMo-V2.6-Flash | Xiaomi | 39.55% | $0.53 | — | $0.14 / $0.28 |
| 21 | Mercury 3 | Inception | 39.26% | $2.11 | — | $0.10 / $0.35 |
| 22 | Gemini 3.8 Flash | 38.65% | $15.79 | — | $0.82 / $4.13 | |
| 23 | Kimi K3 | Moonshot AI | 28.59% | $35.75 | — | $0.24 / $11 |
| 24 | Muse Spark Open | Meta | 26.89% | $3.77 | — | $1.25 / $4.25 |
| 25 | BBeam 1.0 | Reflection AI | 22.85% | N/A | — | — |
| 26 | MiniMax-M3 | MiniMax | 20.90% | $8.39 | — | $0.30 / $1.20 |
| 27 | IInkling-Small | Thinky | 10.43% | $1.36 | — | $0.45 / $1.20 |
| 28 | IInkling | Thinky | 8.82% | $6.13 | — | $1 / $4.05 |
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview

