Codesota · Models · GPT-5.2OpenAI3 results · 2 benchmarks
Model card

GPT-5.2.

OpenAIapiUndisclosed params
§ 02 · Benchmarks

Every benchmark GPT-5.2 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SWE-benchComputer Code · Code Generationresolve-rate-agentic80.0%#4/252026-02-01source ↗
02SWE-benchComputer Code · Code Generationresolve-rate80.0%#6/322026-02-01source ↗
03SWE-bench VerifiedAgentic AI · SWE-benchresolve-rate80.0%#6/81source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where GPT-5.2 actually performs.

Computer Code
1
benchmark
avg rank #5.0
Agentic AI
1
benchmark
avg rank #6.0
§ 04 · Papers

1 paper with results for GPT-5.2.

  1. 2023-10-10· Computer Code· 1 result

    SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

    Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.
§ 05 · Related models

Other OpenAI models scored on Codesota.

GPT-4o
Undisclosed params · 38 results · 9 SOTA
o3
17 results · 5 SOTA
o4-mini
14 results · 2 SOTA
o3 (high)
2 results · 1 SOTA
Codex / GPT-5.5
1 result · 1 SOTA
Codex CLI (GPT-5.5)
1 result · 1 SOTA
o4-mini (high)
1 result · 1 SOTA
o1
12 results
§ 06 · Sources & freshness

Where these numbers come from.

openai-internal
1
result
swebench-leaderboard
1
result
editorial
1
result
3 of 3 rows marked verified.