Skip to content

Benchmark

Agentset Embedding Elo - business reports

Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Higher scores are better.

Models measured
15
Scores recorded
15
Sources
1
IQ weight
No weight published

Score distribution

1,500
Mean
1,500
Median
0
Std dev
1,500
10th percentile
1,500
90th percentile
1,500
Min

Leaderboard

#ModelScore
1BGE M3business reports· Agentset1,500
2Embed Multilingual V3.0business reports· Agentset1,500
3Gemini Embedding 2business reports· Agentset1,500
4Jina Embeddings v3business reports· Agentset1,500
5Jina Embeddings v5 Text Smallbusiness reports· Agentset1,500
6Qwen3 Embedding 0.6Bbusiness reports· Agentset1,500
7Qwen3 Embedding 4Bbusiness reports· Agentset1,500
8Qwen3 Embedding 8Bbusiness reports· Agentset1,500
9Text Embedding 004business reports· Agentset1,500
10Text Embedding 3 Largebusiness reports· Agentset1,500
11Text Embedding 3 Smallbusiness reports· Agentset1,500
12voyage-3-largebusiness reports· Agentset1,500
13voyage-3.5business reports· Agentset1,500
14voyage-3.5-litebusiness reports· Agentset1,500
15voyage-4business reports· Agentset1,500