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

DeepSWE: Unspecified

Benchmark Family
DeepSWE
Version or Variant
Unknown
Canonical Reference
deepswe/default
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-00154-001 GPT-5.4 DeepSWE Resolved 52% ±2% Unknown Primary source OPNAI-54
BR-00155-013 GPT-5.5 DeepSWE Resolved 67% ±6% Unknown Primary source OPNAI-55
BR-00156LN-001 GPT-5.6 Luna DeepSWE Resolved 67% ±4% Unknown Primary source OPNAI-56LN
BR-00156SL-001 GPT-5.6 Sol DeepSWE Resolved 73% ±3% Unknown Primary source OPNAI-56SL
BR-00156TR-001 GPT-5.6 Terra DeepSWE Resolved 70% ±3% Unknown Primary source OPNAI-56TR
BR-002FB5-001 Claude Fable 5 DeepSWE Resolved 70% ±4% Unknown Primary source ANTHR-FB5
BR-002O48-022 Claude Opus 4.8 DeepSWE Resolved 59% ±2% Unknown Primary source ANTHR-O48
BR-002S46-001 Claude Sonnet 4.6 DeepSWE Resolved 30% ±4% Unknown Primary source ANTHR-S46
BR-002S5-002 Claude Sonnet 5 DeepSWE Resolved 54% ±4% Unknown Primary source ANTHR-S5
BR-00331P-020 Gemini 3.1 Pro DeepSWE Resolved 12% ±2% Unknown Primary source GOOGL-G31P
BR-00335F-003 Gemini 3.5 Flash DeepSWE Resolved 37% ±2% Unknown Primary source GOOGL-G35F
BR-00737-011 Qwen3.7-Max DeepSWE Resolved 18 Unknown Primary source QWEN-37
BR-010K27CODE-001 Kimi K2.7-code DeepSWE Resolved 31% ±1% Unknown Primary source KIMI-K27CODE
BR-01152-001 GLM-5.2 DeepSWE Resolved 44% ±2% Unknown Primary source GLM-52
BR-01152-012 GLM-5.2 DeepSWE Resolved 46.2 Unknown Primary source GLM-52