benchmark-radar good first issues (Python)

help wanted urgent

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

adding a draggable divider between two sections on the homepage, so users can resize them by dragging left or right 3 days ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[3 points] 需要补充脑机接口 bench的saturation 11 days ago

good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

feedback about 1 month ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

Alina suggestion about 2 months ago

help wanted new feature slim

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[12 points] Contribute one original analysis section to the next technical report (issue ASSIGNED TO issue 已经交给 pengqianhan.) about 2 months ago

help wanted paper

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[6 points each] Call for real Benchmark Radar use cases and report collaborators / 征集真实使用案例与报告协作者 about 2 months ago

help wanted traction

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[12 points] Audit report finding 6.2: which near-ceiling scores survive protocol controls? about 2 months ago

help wanted paper

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[8 points] Audit report finding 6.1: has vendor attention converged on a benchmark core? about 2 months ago

help wanted paper

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[12 points] Paper study: identify agent weaknesses and measurement gaps / Agent 弱点研究 about 2 months ago

help wanted paper use-case

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[2 points] [Benchmark submission] FrontierChallenge — end-to-end scientific workflow completion for AI agents about 2 months ago

good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[12 points] Paper study: test LLM trends with protocol-aware scores / LLM 趋势研究 about 2 months ago

help wanted paper use-case

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[8 points] Paper study: map prior art for a new benchmark / 新 Benchmark 前序研究 about 2 months ago

help wanted paper use-case

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[6 points] Paper study: choose benchmarks for a real industry agent / 业界 Agent 评测选型 about 2 months ago

help wanted paper use-case

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

[3 points] hy4 about 2 months ago

good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

添加其他信息源 about 2 months ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

add or crawl some new bench from https://github.com/modelscope/evalscope about 2 months ago

help wanted friends

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

中文的issue template注释 2 months ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

Give every release a one-line summary a reader can scan 2 months ago

help wanted new feature

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

再补充几个 bench， 2 months ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

readme update 添加动图 2 months ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

readme update 2 months ago

help wanted

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

help wanted dependencies new feature

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

Add model card: https://ollama.com/library/qwen3.8 2 months ago

good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

Audit single-adopter benchmarks for under-counted edges 3 months ago

help wanted good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

Fill in missing benchmark URLs and release dates, or record that none exist 3 months ago

good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

Add recent model cards for under-covered vendors 3 months ago

help wanted good first issue model-card

ktwu01/benchmark-radar

7

Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.

Python

#ai-benchmark#datasets#evaluation#research-radar

ktwu01/benchmark-radar

Open Issues Need Help