Repository Issue Activity (beta)

#4842 [Research Project] MOEB: Massive Omni Embedding Benchmark

#5492 Current status of contamination and recommendation whether to use training sets

#5358 MOEB [Paper Experiment] - Modality Equivalence

#5487 Add model: linkup-sparseup

#3424 Make all `retrieval` datasets compatible with v2 format

#5482 reduce time to create `uv.lock`

#5471 Add citation validation

#5451 Evaluation request — tencent/EVIE-8B and tencent/EVIE-4.5B on ViDoRe(v3) private tasks

#5460 How should we handle audio longer than a model can process?

#5468 New windows test is unstable or fails

#5092 A constant scorer gets mrr_at_10 = 1.0 on WebLINXCandidatesReranking due to inconsistent tie-breaking

#5457 Add dataset: NayanaIR MonoBench (8 Indic languages)

#5254 Omnimodal wikipedia

#2709 Integrate `ColDeR`

#5359 MOEB [Paper Experiment] - Modality Gap in Omni-Models

#5360 MOEB [Paper Experiment] - Directional Asymmentry

#5408 Add Pareto identifier to models

#5433 Add dataset: Flickr Audio-Image-Text Retrieval (A2IT / IT2A)

#2907 Can not reproduce Qwen3-Embedding results

#5302 Add model: WeMM-Embedding

#3628 Add dataset: ToolRetrieval

#5143 Add dataset: BioVITA

#5442 Add OpenMDW-1.1 to MTEB’s recognized open licenses

#5416 Quality Concerns in 11 MMTEB Datasets

#5063 Make a low-dependency version of of MTEB