Who leads the STS Benchmark benchmark?

GTE-Qwen2-7B-instruct currently leads STS Benchmark with a score of 88.4 on Spearman.

What is the state-of-the-art score on STS Benchmark?

The state-of-the-art result on STS Benchmark is 88.4 (Spearman), achieved by GTE-Qwen2-7B-instruct as of 2024.

How many models are tracked on STS Benchmark?

Codesota tracks 3 models on STS Benchmark.

When was the STS Benchmark leaderboard last updated?

The STS Benchmark leaderboard on Codesota includes results through 2024, with the earliest tracked result from 2022.

Codesota · Benchmark · STS BenchmarkHome/Leaderboards/STS Benchmark

Unknown

STS Benchmark.

Name: STS Benchmark Benchmark Results
Creator: Unknown
Published: 2022-01-01
License: https://creativecommons.org/licenses/by/4.0/

Semantic textual similarity with human-annotated sentence pairs

Paper ↗Leaderboard ↓

§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Only 3 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 ↗

Spearman

Spearman is the reported evaluation metric for STS Benchmark. 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 Spearmanverifiedpapervendorcommunityunverified

Rank	Model	Trust	Score	Year	Links	Fix
01	GTE-Qwen2-7B-instruct GTE-Qwen2-7B Spearman on STS Benchmark test split. MTEB STS sub-task average.	verified	88.4	2024	Source ↗	Looks wrong?
02	E5-Mistral-7B-instruct E5-Mistral-7B Spearman on STS Benchmark. From MTEB STS sub-task results.	verified	84.7	2024	Source ↗	Looks wrong?
03	all-MiniLM-L6-v2 all-MiniLM-L6-v2 Spearman on STS Benchmark test. From official model card.	verified	82.8	2022	Source ↗	Looks wrong?

§ 04 · Submit a result

Add to the leaderboard.

← Back to Leaderboards