Benchmark · Knowledge

SWE-Bench Pro (Private)

Updated 2025-11-24
Models tested
2
Top score
23.4
Claude Opus 4.5
Median
16.8
min 10.1
Top-5 spread
σ 6.7
wide open
SWE-BENCH PRO (PRIVATE) \u00B7 TOP 20255075100#1Claude Opus 4.523.4#2Gemini 2.5 Pro Preview …10.1benchgecko.ai/benchmark/seal-swe-bench-pro-private

2 models tested · sorted by score

Same category · related evaluations