{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.06538", "kind": "paper", "url": "https://arxiv.org/abs/2606.06538"}, {"id": "gh:zlab-princeton/worldbench", "kind": "repo", "url": "https://github.com/zlab-princeton/WorldBench"}, {"kind": "website", "url": "https://worldbench-vl.github.io/"}], "authors": ["Yida Yin", "Harish Krishnakumar", "Chung Peng Lee", "Boya Zeng", "Wenhao Chai", "Shengbang Tong", "Wenhu Chen", "Hu Xu", "Xingyu Fu", "Gabriel Sarch", "Aleksandra Korolova", "Zhuang Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.06538", "source_url": "https://arxiv.org/abs/2606.06538"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "WorldBench evaluates multimodal large language models on visually diverse reasoning questions, with accuracy as the metric on a curated dataset."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.06538", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.06538", "title": "WorldBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.06538", "modality": null, "name": "WorldBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_worldbench_a7ecd2c0", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4e283b9e52fa7a33f0d9b56801bdabb5ac9479ed027c14f7f0598547afbb620b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.06538"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.06538", "source_url": "https://arxiv.org/abs/2606.06538"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-06538", "source": "claire_radar", "source_benchmark_id": "2606.06538", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/zlab-princeton/WorldBench", "githubScope": "benchmark_repo", "githubStars": 8, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 4, "hfPaperUrl": "https://huggingface.co/papers/2606.06538", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "ad7c7d3a2f428b2672931cdfa4ebc4cfd6b312c59e445e9628866908c7b7007b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WorldBench evaluates multimodal large language models on visually diverse reasoning questions, with accuracy as the metric on a curated dataset.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We present WorldBench, a challenging and visually diverse reasoning benchmark to evaluate Multimodal Large Language Models (MLLMs)."}, "familyId": "bmf_365c8ee11b3d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/zlab-princeton/WorldBench", "url": "https://worldbench-vl.github.io/"}], "scope": "benchmark_repo", "url": "https://github.com/zlab-princeton/WorldBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_worldbench_a7ecd2c0", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/zlab-princeton/WorldBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.06538", "paper": "https://arxiv.org/abs/2606.06538", "pdf": "https://arxiv.org/pdf/2606.06538", "project": "https://worldbench-vl.github.io/", "report": "https://arxiv.org/abs/2606.06538"}, "metrics": [], "motivation": "In real-world applications, models are expected to perform reliably across diverse settings.", "name": "WorldBench", "oneLine": "WorldBench evaluates multimodal large language models on visually diverse reasoning questions, with accuracy as the metric on a curated dataset.", "paperTitle": "WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.06538", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-04", "source": {"authors": ["Yida Yin", "Harish Krishnakumar", "Chung Peng Lee", "Boya Zeng", "Wenhao Chai", "Shengbang Tong", "Wenhu Chen", "Hu Xu", "Xingyu Fu", "Gabriel Sarch", "Aleksandra Korolova", "Zhuang Liu"], "categories": ["cs.CV"], "id": "2606.06538", "title": "WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark", "type": "arxiv", "url": "https://arxiv.org/abs/2606.06538"}, "sourceUpdatedAt": "2026-06-04T01:11:21Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "Highlights visual diversity gaps in existing benchmarks; provides a challenging fixed dataset for model comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
