Aider Polyglot
Harbor nativeAider Polyglot: 6种语言diff编辑
Verified71%Coding
- Samples
- 225
- Released
- 2024
- Scores
- 61
WebApp1K-React
Test-driven benchmark to challenge LLMs to write JavaScript React application
How to run
ltb · webapp1k-react
$ npm i -g lettokenburn-cli$ ltb bench info webapp1k-react
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
8 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| o1 | 95.2 | N/A | Independent | medium | Sep 19, 2024 | arxiv.org |
| o1-mini | 93.9 | N/A | Independent | medium | Sep 19, 2024 | arxiv.org |
| GPT-4o | 88.5 | N/A | Independent | medium | Sep 8, 2024 | arxiv.org |
| Claude 3.5 Sonnet | 88.1 | N/A | Independent | medium | Sep 8, 2024 | arxiv.org |
| DeepSeek V2.5 | 83.4 | N/A | Independent | medium | Sep 19, 2024 | arxiv.org |
| Mistral Large 2 | 78.0 | N/A | Independent | medium | Sep 8, 2024 | arxiv.org |
| DeepSeek Coder V2 | 70.0 | N/A | Independent | medium | Sep 8, 2024 | arxiv.org |
| Llama V3P1 405B Instruct | 30.2 | N/A | Independent | medium | Sep 8, 2024 | 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
Test-driven benchmark to challenge LLMs to write JavaScript React application