BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases7

Code Migration leaderboard

As of 6 Nov 2026, the top score on Code Migration is 69.8% by Claude Sonnet 5.5 (Anthropic), ahead of Gemini 4 Argon at 68.2%, across 77 model configurations with a published result (Vals AI, result dated 29 Oct 2026). The model receives a working program and must port it to a different language; the port is checked against the original test suite. Code Migration is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 6 Nov 2026)

  • Claude Sonnet 5.5 holds the top Code Migration score at 69.8% (Vals AI, 29 Oct 2026).
  • Gemini 4 Argon is second on Code Migration at 68.2% (Vals AI, 29 Oct 2026).
  • Code Migration: Rewriting whole programs in another language so they still pass the tests. Run by Vals AI (Vals AI).
  • 77 model configurations have a published Code Migration result on BenchLeader (BenchLeader, 6 Nov 2026).
  • Code Migration does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Rewriting whole programs in another language so they still pass the tests. Run by Vals AI.

Published by
Vals AI
Category
Coding
Index weight
Reference only
Models
77
Data as of
6 Nov 2026

Vals AI (vals.ai).

What the test looks like

The model receives a working program and must port it to a different language; the port is checked against the original test suite.

How it is scored

Percent of migrations passing, run by Vals AI.

What to keep in mind

A specific engineering skill; strong scores here do not imply strong algorithmic coding.

Top 15
  1. 1Claude Sonnet 5.569.8%
  2. 2Gemini 4 Argon (high)68.2%
  3. 3GPT-6 Astra (max)67.7%
  4. 4Claude Opus 5.566.7%
  5. 5GPT-6.1 Sol (max)65.1%
  6. 6Muse Wonder (max)62.5%
  7. 7Muse Wonder Full (max)61.0%
  8. 8Claude Opus 557.5%
  9. 9GPT-6 Sol (max)57.2%
  10. 10Claude Fable 555.1%
  11. 11Claude Fable 5.154.6%
  12. 12GPT-5.6 Sol (max)52.9%
  13. 13GPT-5.6 Terra (max)47.8%
  14. 14Hy447.4%
  15. 15Muse Spark 1.3 (max)47.4%
77 of 77
#
1Claude Sonnet 5.569.8%–$75.832026-10-29
2Gemini 4 Argonhigh68.2%66.0$57.822026-10-29
3GPT-6 Astramax67.7%67.8$44.362026-10-29
4Claude Opus 5.566.7%63.4$112.972026-10-29
5GPT-6.1 Solmax65.1%67.3$6.512026-10-29
6Muse Wondermax62.5%62.3$69.542026-10-29
7Muse Wonder Fullmax61.0%62.9$38.412026-10-29
8Claude Opus 557.5%65.2$60.512026-10-29
9GPT-6 Solmax57.2%63.3$15.682026-10-29
10Claude Fable 555.1%66.5$112.102026-10-29
11Claude Fable 5.154.6%66.4$70.972026-10-29
12GPT-5.6 Solmax52.9%65.4$24.542026-10-29
13GPT-5.6 Terramax47.8%60.7$8.132026-10-29
14Hy447.4%55.7$3.412026-10-29
15Muse Spark 1.3max47.4%62.0$14.212026-10-29
16Claude Opus 4.847.3%60.0$30.512026-10-29
17DeepSeek V4.1 Flashhigh45.6%55.7$0.9452026-10-29
18GPT-5.5xhigh45.2%64.3$6.442026-10-29
19Grok 4.7xhigh44.8%58.3$36.552026-10-29
20Grok 4.6high44.6%60.5$14.582026-10-29
21Claude Haiku 5.544.6%–$6.232026-10-29
22GPT-5.6 Lunamax44.5%56.3$1.882026-10-29
23Claude Sonnet 544.4%55.9$35.312026-10-29
24GLM 5.3max44.2%59.0$24.912026-10-29
25DeepSeek V4.1 Flash 1017max44.2%59.2$1.862026-10-29
26Claude Opus 4.743.9%63.1$36.392026-10-29
27MiMo-V2.6-Pro43.0%57.3$0.6922026-10-29
28GPT-6 Lunamax42.5%56.7$0.6012026-10-29
29DeepSeek V4 Promax41.5%57.0$18.582026-10-29
30MiMo-V2.6-Flash40.9%55.0$0.4942026-10-29
31Claude Sonnet 4.639.9%58.2$38.512026-10-29
32Step 5 Preview39.0%54.9$7.612026-10-29
33DeepSeek V4 Flashhigh38.6%57.3$3.612026-10-29
34GLM 5.2max37.9%59.5$12.642026-10-29
35Grok 4.5high36.6%56.9$3.372026-10-29
36Gemini 3.8 Flashhigh36.5%62.0$18.492026-10-29
37GPT-5.4xhigh35.0%63.2$7.762026-10-29
38Gemini 3.7 Flashhigh34.8%62.2$21.462026-10-29
39Ember-132.5%–$51.112026-10-29
40Muse Spark 1.1xhigh31.1%59.5$4.562026-10-29
41Gemini 3.6 Flashhigh30.9%61.2$8.932026-10-29
42Mistral Large 4high30.6%49.5$24.522026-10-29
43Muse Spark 1.2xhigh29.9%61.7$3.782026-10-29
44Kimi K2.627.8%55.2$5.112026-10-29
45Muse Spark 1.3xhigh27.6%58.5$4.622026-10-29
46Gemini 3.5 Flashhigh26.8%62.5$5.732026-10-29
47GLM 5.125.8%55.7$5.702026-10-29
48Kimi K2.7 Code25.4%54.2$5.042026-10-29
49Qwen3.8 Maxmax24.0%58.8$10.542026-10-29
50MiMo-V2.5-Pro21.6%54.9$0.2382026-10-29
51Muse Spark Openxhigh21.2%54.0$9.042026-10-29
52GLM 5.3 Flashmax20.5%54.2$6.262026-10-29
53MiniMax M319.9%56.4$7.072026-10-29
54Gemini 3.1 Prohigh17.3%60.1$1.612026-10-29
55Kimi K3max16.1%62.1$13.872026-10-29
56GPT-5.4 Nanohigh14.5%48.3$0.4162026-10-29
57Qwen3.8 27Bxhigh14.2%52.5$21.682026-10-29
58Inkling Small13.7%52.1$0.5972026-10-29
59Qwen3.7max13.1%60.3$1.932026-10-29
60GPT-5.4 Minixhigh12.9%56.0$1.952026-10-29

More coding benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on Code Migration

Cite as: BenchLeader, “Code Migration leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/vals_code_migration.

Code Migration: questions

What does Code Migration measure?
The model receives a working program and must port it to a different language; the port is checked against the original test suite. Scores are reported in percent of tasks solved; higher is better.
What is the top score on Code Migration?
As of 6 Nov 2026, the highest score on Code Migration is 69.8% by Claude Sonnet 5.5 (result dated 29 Oct 2026), ahead of Gemini 4 Argon at 68.2%. Scores come from Vals AI and are re-read daily.
Which AI model leads Code Migration?
Claude Sonnet 5.5 leads Code Migration with 69.8% as of 6 Nov 2026 (result dated 29 Oct 2026), ahead of Gemini 4 Argon at 68.2%.
How many models have Code Migration results?
77 model configurations have a Code Migration result on BenchLeader, all taken from Vals AI.
Who runs Code Migration and how often is it updated?
Code Migration is published by Vals AI. BenchLeader re-reads the published results once a day and records the date each result was published.
Does Code Migration count toward the BenchLeader Index?
No. Code Migration is shown for reference but left out of the composite index.