CodeContests
Code Contests (DeepMind)
CodeContests: DeepMind编程竞赛
How to run
ltb · codecontests
$ npm i -g lettokenburn-cli$ ltb bench run [email protected] --benchmark codecontests -a claude-code -m anthropic/claude-opus-4-8$ ltb bench push
Harbor-native: you can also call Harbor directly.
harbor
$ harbor run -d [email protected] -a claude-code -m anthropic/claude-opus-4-8
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
1 sourced entry| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| WizardCoder 15B | 1.1 | N/A | Independent | medium | Jun 14, 2023 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
CodeContests (Code Contests (DeepMind)) — DeepMind编程竞赛. Scoring: Pass@1. Difficulty: 极高. Imported from benchmark_research.md (2026-06).