BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

SWE-bench: Multilingual

Benchmark Family
SWE-bench
Version or Variant
Multilingual
Canonical Reference
swe-bench/multilingual
Release Date
Unknown
Status
ACTIVE

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-002O47-003 Claude Opus 4.7 SWE-bench Multilingual Resolved 80.5% Unknown Primary source ANTHR-O47
BR-002O48-003 Claude Opus 4.8 SWE-bench Multilingual Resolved 84.4 Unknown Primary source ANTHR-O48
BR-005C2-002 Composer 2 SWE-bench Multilingual Resolved 73.7 Unknown Primary source CURSR-C2
BR-00735-029 Qwen3.5-397B-A17B SWE-bench Multilingual Resolved 69.3 Unknown Primary source QWEN-35
BR-008V4FLASH-017 DeepSeek V4-Flash SWE-bench Multilingual Resolved 73.3 Unknown Primary source DPSK-V4FLASH
BR-008V4PRO-017 DeepSeek V4-Pro SWE-bench Multilingual Resolved 76.2 Unknown Primary source DPSK-V4PRO