Codesota · Benchmark · MS MARCOHome/Leaderboards/MS MARCO
Unknown

MS MARCO.

Large-scale passage ranking benchmark from Bing search queries

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Only 4 models on this benchmark
Help build the community leaderboard — submit your model results.
Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Mrr@10

Mrr@10 is the reported evaluation metric for MS MARCO. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Mrr@10verifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01RankLLaMA-7B
RankLLaMA-7B MRR@10 MS MARCO dev. Paper reports beating RankT5 (40.3) by 1.5 pts.
verified41.82023Source ↗Looks wrong?
02jina-reranker-v2-base-multilingual
Jina-reranker-v2-base-multilingual MRR@10 on MS MARCO dev set from Jina AI model page.
verified41.22024Source ↗Looks wrong?
03ColBERTv2
ColBERTv2 MRR@10 on MS MARCO dev set. From original paper Table 2.
verified39.72022Source ↗Looks wrong?
04MonoT5-3B
MonoT5-3B MRR@10 on MS MARCO passage dev (full set). Castorini pygaggle experiments.
verified392020Paper ↗Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards