BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases12

Code Migration v1.1

Code Migration v1.1, the version Vals AI now runs new models on. Run by Vals AI.

As of 24 Oct 2026, Claude Sonnet 5.5 leads Code Migration v1.1 on BenchLeader with 86.9%, ahead of Claude Opus 5.5 at 81.0%, across 26 model configurations with a published result.

Published by
Vals AI
Category
Coding
Index weight
Reference only
Models
26
Data as of
24 Oct 2026
Newest result
20 Oct 2026

Vals AI (vals.ai).

Top 15
  1. 1Claude Sonnet 5.586.9%
  2. 2Claude Opus 5.581.0%
  3. 3GPT-6 Astra (max)80.6%
  4. 4GPT-6.1 Sol (max)77.3%
  5. 5Muse Wonder (max)72.4%
  6. 6Gemini 4 Argon (high)70.8%
  7. 7DeepSeek V4.1 Flash 1017 (max)67.5%
  8. 8Muse Wonder Full (max)62.8%
  9. 9DeepSeek V4.1 Flash (max)58.9%
  10. 10Qwen3.8 Max Internal57.2%
  11. 11GLM 5.3 (max)55.1%
  12. 12Grok 4.7 (xhigh)53.2%
  13. 13Claude Haiku 5.552.4%
  14. 14DeepSeek V4 Pro (max)52.0%
  15. 15GLM 5.3 Flash (max)51.6%
26 of 26
#
1Claude Sonnet 5.586.9%–2026-10-20
2Claude Opus 5.581.0%62.02026-10-20
3GPT-6 Astramax80.6%70.42026-10-20
4GPT-6.1 Solmax77.3%69.92026-10-20
5Muse Wondermax72.4%67.52026-10-20
6Gemini 4 Argonhigh70.8%70.82026-10-20
7NewDeepSeek V4.1 Flash 1017max67.5%64.02026-10-20
8Muse Wonder Fullmax62.8%70.72026-10-20
9DeepSeek V4.1 Flashmax58.9%61.22026-10-20
10NewQwen3.8 Max Internal57.2%–2026-10-20
11GLM 5.3max55.1%63.52026-10-20
12Grok 4.7xhigh53.2%61.62026-10-20
13Claude Haiku 5.552.4%–2026-10-20
14DeepSeek V4 Promax52.0%60.82026-10-20
15GLM 5.3 Flashmax51.6%54.22026-10-20
16MiMo-V2.6-Pro48.8%64.02026-10-20
17Step 5 Preview47.0%60.42026-10-20
18GPT-6 Lunamax46.7%60.02026-10-20
19MiMo-V2.6-Flash39.5%59.72026-10-20
20NewMercury 3high39.3%–2026-10-20
21Gemini 3.8 Flashhigh38.6%64.42026-10-20
22Kimi K3max28.6%64.72026-10-20
23Muse Spark Openxhigh26.9%62.02026-10-20
24NewBeam 1.022.9%51.12026-10-20
25MiniMax M320.9%56.42026-10-20
26Inkling Small10.4%54.82026-10-20

More coding benchmarks · All LLM benchmarks

Cite as: BenchLeader, “Code Migration v1.1 leaderboard”, data as of 24 Oct 2026, https://www.benchleader.com/benchmarks/vals_code_migration_11.

Code Migration v1.1: questions

What does Code Migration v1.1 measure?
Code Migration v1.1, the version Vals AI now runs new models on. Run by Vals AI. Scores are reported in percent of tasks solved; higher is better.
Which AI model leads Code Migration v1.1?
Claude Sonnet 5.5 leads Code Migration v1.1 with 86.9% as of 24 Oct 2026, ahead of Claude Opus 5.5 at 81.0%.
How many models have Code Migration v1.1 results?
26 model configurations have a Code Migration v1.1 result on BenchLeader, all taken from Vals AI.
Who runs Code Migration v1.1 and how often is it updated?
Code Migration v1.1 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 v1.1 count toward the BenchLeader Index?
No. Code Migration v1.1 is shown for reference but left out of the composite index.