Codesota · Benchmark · TransCoder (GeeksForGeeks)Home/Leaderboards/Code & Software Engineering/Code Translation/TransCoder (GeeksForGeeks)
Unknown

TransCoder (GeeksForGeeks).

Code translation benchmark between C++, Java, and Python using 852 GeeksForGeeks programming problems. Each function has correct implementations in all three languages. Primary metric is Computational Accuracy (CA) — translated code must pass all unit tests.

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Computational Accuracy

Computational Accuracy is the reported evaluation metric for TransCoder (GeeksForGeeks). Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Computational Accuracyverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01Claude Sonnet 4
Java→Python translation. Anthropic model card.
verified89.42026Source ↗Looks wrong?
02GPT-4o
Java→Python translation. Reported in DeepSeek-Coder-V2 comparative table.
verified88.22024Paper ↗Code ↗Looks wrong?
03Qwen2.5-Coder 32B
Java→Python translation. Qwen2.5-Coder paper.
verified86.32024Paper ↗Code ↗Looks wrong?
04DeepSeek-Coder-V2-Instruct
Java→Python translation. DeepSeek-Coder-V2 paper.
verified84.62024Paper ↗Code ↗Looks wrong?
05StarCoder2 15B
Java→Python translation. StarCoder2 paper. Instruction-tuned model.
verified78.42024Paper ↗Code ↗Looks wrong?
06CodeT5+
Java→Python translation. CodeT5+ paper (220M encoder-decoder variant).
verified72.12023Paper ↗Code ↗Looks wrong?
07TransCoder
Java→Python translation. TransCoder paper Table 3. CA (% of functions passing tests).
verified68.72020Paper ↗Code ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Code Translation