Benchmark profile

Vals Code Migration (Code Migration)

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

Data verified July 10, 2026

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 10, 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.

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

Code Migration on Vals AI Vals methodology Vals home

Code Migration score on Code Migration — July 10, 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.

Claude Fable 5

Anthropic

anthropic/claude-fable-5

55.06%

Overall —

GPT-5.6 Sol

OpenAI

openai/gpt-5.6-sol

52.92%

Overall —

Claude Opus 4.8

Anthropic

anthropic/claude-opus-4-8

47.25%

Overall —

30 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated July 10, 2026

Code Migration score table (30 models)

Score

Claude Fable 5Anthropic

55.06%

GPT-5.6 SolOpenAI

52.92%

Claude Opus 4.8Anthropic

47.25%

GPT-5.5OpenAI

45.16%

GPT-5.6 LunaOpenAI

44.55%

Claude Sonnet 5Anthropic

44.39%

Claude Opus 4.7Anthropic

43.88%

Claude Sonnet 4.6Anthropic

39.89%

GLM 5.2Zhipu AI

37.87%

Grok 4.5SpaceXAI

36.60%

GPT-5.6 TerraOpenAI

36.45%

GPT-5.4OpenAI

34.98%

Muse Spark 1 1Meta

31.11%

Kimi K2.6Moonshot AI

27.77%

Gemini 3.5 FlashGoogle

26.75%

DeepSeek V4 ProDeepSeek

26.20%

GLM 5.1Zhipu AI

25.77%

Kimi K2.7 CodeMoonshot AI

25.39%

Mimo V2.5 ProXiaomi

21.56%

MiniMax M3MiniMax

19.93%

Gemini 3.1 Pro PreviewGoogle

17.31%

Mimo V2.5Xiaomi

14.23%

GPT-5.4 MiniOpenAI

12.94%

InklingThinkingmachines

11.79%

Qwen3.6 PlusAlibaba

11.10%

MiniMax M2.7MiniMax

8.69%

Claude Haiku 4.5 20251001 ThinkingAnthropic

7.55%

Grok 4.3SpaceXAI

6.79%

Gemini 3 Flash PreviewGoogle

6.39%

Gemini 3.1 Flash Lite PreviewGoogle

4.61%

The published Code Migration snapshot places Claude Fable 5 first at 55.06%. The third row is 7.81 points behind. The broader top-10 range is 18.47 points, so the table still separates the published systems.

30 models have been evaluated on Code Migration. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. 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.

Code Migration Public benchmark source

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.

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?

30 AI models are included in BenchLM's mirrored Code Migration snapshot, based on the public leaderboard captured on July 10, 2026.

Last updated: July 10, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.