Code Migration
Results
26 of 41 tracked models have a result.
- 1
Anthropic · Max effort
70.1% - 2Gemini 4 ArgonLimited
Google DeepMind · High effort
69.5% - 3
Anthropic · Max effort
68.9% - 4
OpenAI · Max effort
68.5% - 5
OpenAI · Max effort
63.3% - 6
Anthropic · Max effort
60.0% - 7
Meta · Max effort
48.3% - 8
OpenAI · Max effort
48.3% - 9
DeepSeek · High effort
46.9% - 10Hy4 previewOpen
Tencent
46.8% - 11
Anthropic · Max effort
45.9% - 12
OpenAI · Max effort
44.4% - 13GLM-5.3Open
Z.ai · Max effort
43.2% - 14
SpaceXAI · xHigh effort
43.2% - 15MiMo-V2.6-ProOpen
Xiaomi
42.3% - 16DeepSeek V4 ProOpen
DeepSeek · Max effort
41.6% - 17MiMo-V2.6-FlashOpen
Xiaomi
40.4% - 18
StepFun
39.5% - 19
Google DeepMind · High effort
31.6% - 20
Alibaba
23.2% - 21
Mistral AI · High effort
22.8% - 22MiniMax-M3Open
MiniMax
20.9% - 23
Google DeepMind · High effort
17.9% - 24Kimi K3Open
Moonshot AI · Max effort
16.0% - 25Inkling-SmallOpen
Thinking Machines Lab
13.3% - 26InklingOpen
Thinking Machines Lab
11.8%
15 tracked models without a result
Command A+, Gemini 3.5 Flash-Lite, Gemma 4 31B, GLM-5.3-Flash, gpt-oss-120b, Hy3, Kimi K2.7 Code, MAI-Thinking-1, Mistral Medium 3.5, Mistral Small 4, Muse Glimmer 30B, Nemotron 3 Ultra, Nova 2 Lite, Qwen3.8-27B, Qwen3.8-Flash.
Missing means the evaluator has not published a run, not that the model would score poorly.