Six Navers Lab / Einsia benchmarks and the work they test
Compare the tasks, scoring and evidence behind six Einsia benchmarks, with complete Radar detail pages and original references.
Claire Radar
WeaveBench
WeaveBench evaluates computer-use agents on 114 long-horizon tasks across 8 real-world work domains. Each task interleaves GUI interaction with command-line and code operations in a single trajectory, with scoring based on a trajectory-aware judge that detects fabricated evidence.
Evidence available for this benchmark
Numeric results have not been collected for this source record. Use the paper, code or dataset below to check the task and experiments; this does not imply that the original work contains no results.
Start with these resources
- Paper · task design and experiments
- Code · implementation and instructions
- Dataset · files and documentation
- Project page
Cited documents and dates (1)
Catalog collected on 2026-10-14; resources and fields reflect that saved source.
Recorded attention
Observed on: 2026-10-13
- GitHub stars
- 170
- Hugging Face paper upvotes
- 49
- Hugging Face downloads · 30 days before observation
- 1,940
- Star change · 30 days before observation
- +7
weavebench/weavebench · View source snapshot
Dated attention observations, not live counts or benchmark scores.
Evaluation context and evidence
- Source
- Claire Radar
- Publisher
- Not recorded
- Benchmark release
- 2026-06-08
- Collected
- 2026-10-14
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.