Skip to main content
Benchmark Registry
Models
Benchmarks
Organizations
Search the registry
Search
SWE-bench
Benchmark
SWE-bench
Evaluated by
Princeton University
Release date
May 6, 2025
Version
SWE-bench Multilingual
Metric
Resolved Tasks
Search models
Search
Results
4 results
Rows per page
50
100
500
Apply
Latest
History
All providers
Alibaba (Tongyi)
Anthropic
Cursor
DeepSeek AI
MiniMax
Mistral AI
Moonshot AI
NVIDIA
Z.ai
SWE-bench Multilingual results
Provider
Model
Score
Source
Registry No.
Cursor
Composer 2.5
79.8%
Source
for Composer 2.5 on SWE-bench Multilingual
(opens in a new tab)
50004
Cursor
Composer 1
56.9%
Source
for Composer 1 on SWE-bench Multilingual
(opens in a new tab)
50001
Cursor
Composer 1.5
65.9%
Source
for Composer 1.5 on SWE-bench Multilingual
(opens in a new tab)
50002
Cursor
Composer 2
73.7%
Source
for Composer 2 on SWE-bench Multilingual
(opens in a new tab)
50003
Previous
Page
1
of
1
Next