Skip to main content

Vals Code Migration (Code Migration)

Can language models reimplement real-world programs in another language?

Data verified

How BenchLM shows Code Migration

BenchLM mirrors the public Vals AI Code Migration leaderboard captured from https://www.vals.ai/benchmarks/code-migration and updated by Vals on July 9, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

Code Migration is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

27 Vals rows4 task viewsprivate datasetTasks: Overall, CLI, COBOL, Code QualityDisplay only

Code Migration score on Code Migration — July 9, 2026

BenchLM mirrors the published code migration score view for Code Migration. Claude Fable 5 leads the public snapshot at 55.06% , followed by GPT-5.6 Sol (52.92%) and Claude Opus 4.8 (47.25%). BenchLM does not use these results to rank models overall.

27 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 9, 2026

The published Code Migration snapshot is tightly clustered at the top: Claude Fable 5 sits at 55.06%, while the third row is only 7.81 points behind. The broader top-10 spread is 20.08 points, so the benchmark still separates strong models even when the leaders cluster.

27 models have been evaluated on Code Migration. The benchmark falls in the External benchmark mirrors category. BenchLM tracks this category separately from its weighted global scoring system, so these results are best compared on the dedicated Korean benchmark views. Code Migration is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About Code Migration

Year

2026

Tasks

Real-world program reimplementation in another language

Format

Accuracy score

Difficulty

Production code migration

BenchLM mirrors the public Vals AI Code Migration leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

BenchLM freshness & provenance

Version

Code Migration 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

Code Migration score table (27 models)

1
Claude Fable 5anthropic/claude-fable-5
55.06%
2
GPT-5.6 Solopenai/gpt-5.6-sol
52.92%
3
Claude Opus 4.8anthropic/claude-opus-4-8
47.25%
4
GPT-5.5openai/gpt-5.5
45.16%
5
Claude Sonnet 5anthropic/claude-sonnet-5
44.39%
6
Claude Opus 4.7anthropic/claude-opus-4-7
43.88%
7
Claude Sonnet 4.6anthropic/claude-sonnet-4-6
39.89%
8
GLM 5.2zai/glm-5.2
37.87%
9
GPT-5.6 Terraopenai/gpt-5.6-terra
36.45%
10
GPT-5.4openai/gpt-5.4-2026-03-05
34.98%
11
Muse Spark 1 1meta/muse_spark_1_1
31.11%
12
Kimi K2.6kimi/kimi-k2.6
27.77%
13
Gemini 3.5 Flashgoogle/gemini-3.5-flash
26.75%
14
DeepSeek V4 Prodeepseek/deepseek-v4-pro
26.20%
15
GLM 5.1zai/glm-5.1
25.77%
16
Kimi K2.7 Codekimi/kimi-k2.7-code
25.39%
17
Mimo V2.5 Proxiaomi/mimo-v2.5-pro
21.56%
18
MiniMax M3minimax/MiniMax-M3
19.93%
19
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
17.31%
20
Mimo V2.5xiaomi/mimo-v2.5
14.23%
21
GPT-5.4 Miniopenai/gpt-5.4-mini-2026-03-17
12.94%
22
Qwen3.6 Plusalibaba/qwen3.6-plus
11.10%
23
MiniMax M2.7minimax/MiniMax-M2.7
8.69%
24
Claude Haiku 4.5 20251001 Thinkinganthropic/claude-haiku-4-5-20251001-thinking
7.55%
25
Grok 4.3grok/grok-4.3
6.79%
26
Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
6.39%
27
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
4.61%

FAQ

What does Code Migration measure?

Can language models reimplement real-world programs in another language?

Which model leads the published Code Migration snapshot?

Claude Fable 5 currently leads the published Code Migration snapshot with 55.06% code migration score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on Code Migration?

27 AI models are included in BenchLM's mirrored Code Migration snapshot, based on the public leaderboard captured on July 9, 2026.

Last updated: July 9, 2026 · mirrored from the public benchmark leaderboard

The AI models change fast. We track them for you.

For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.