Rankings / OpenAI
GPT 4o 20241120
release date unknown
BenchAtlas Index
as of 2026-07-14
Benchmark evidence
0 results
Agent + model results
systems, not bare-model scores
| agent + model mini-SWE-agent + GPT 4o 20241120 | SWE-bench Verified | 21.6 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GPT 4o 20241120 | SWE-bench bash-only | 21.6 % | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GPT 4o 20241120 | SWE-bench Verified | 1.5 usd_per_task | community | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GPT 4o 20241120 | SWE-bench bash-only | 1.5 usd_per_task | community | SWE-bench Leaderboard |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.