Pith Number

pith:Z52BXLJP

pith:2022:Z52BXLJPOVYNXCWOMA3GFJLDTO

not attested not anchored not stored refs pending

MTEB: Massive Text Embedding Benchmark

Lo\"ic Magne, Niklas Muennighoff, Nils Reimers, Nouamane Tazi

A new benchmark shows no single text embedding method performs best across all tasks.

arxiv:2210.07316 v3 · 2022-10-13 · cs.CL · cs.IR · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{Z52BXLJPOVYNXCWOMA3GFJLDTO}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks.

C2weakest assumption

The 8 tasks and 58 datasets chosen are sufficiently representative of the full range of real-world embedding applications so that performance on MTEB predicts usefulness elsewhere.

C3one line summary

MTEB is a new multi-task benchmark showing that no single text embedding model leads on all 8 tasks across 58 datasets.

Formal links

1 machine-checked theorem link

Cited by

40 papers in Pith

Query pipeline optimization for cancer patient question answering systems

One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation

Federated Learning for ICD Classification with Lightweight Models and Pretrained Embeddings

SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass

Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding

Receipt and verification

First computed	2026-05-17T23:38:52.799771Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac

Aliases

arxiv: 2210.07316 · arxiv_version: 2210.07316v3 · doi: 10.48550/arxiv.2210.07316 · pith_short_12: Z52BXLJPOVYN · pith_short_16: Z52BXLJPOVYNXCWO · pith_short_8: Z52BXLJP

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/Z52BXLJPOVYNXCWOMA3GFJLDTO \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: cf741bad2f7570db8ace603662a5639bbdb476bcbc363e216b26c2d777f1a6ac

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b9f0eef31e7d1249bfde4e27f63923dc5697cd582fa9ac5ce1b60fe9dea003f8",
    "cross_cats_sorted": [
      "cs.IR",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2022-10-13T19:42:08Z",
    "title_canon_sha256": "c6029532035edb5cd95cc52d76c8c664a42e23bb7c566963351eb1aac851f070"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2210.07316",
    "kind": "arxiv",
    "version": 3
  }
}