GPT-5.2 is the stronger all-rounder.
Scores updated · 9 tests both models report · How we compare
Where each one wins
Tests won in each of the four areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Math and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-5.2 pulls ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+19.7points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+8.4points ahead
- US invitational high-school math exam problemsAIME 2026+5.8points ahead
Where MAI-Code-1-Flash pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+21.3points ahead
Every test, side by side
All 9 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.2
- SWE-bench ProMAI-Code-1-Flash by 21.329.951.2+21.3
- SWE-bench VerifiedGPT-5.2 by 8.48071.6+8.4
- SWE-bench MultilingualGPT-5.2 by 1.266.765.5+1.2
ReasoningGPT-5.2
- Humanity's Last ExamGPT-5.2 by 19.737.718+19.7
- GPQA DiamondGPT-5.2 by 5.790.384.6+5.7
Other results2 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- FrontierMath (overall)GPT-5.2 by 3440.36.3+34
- Terminal-Bench 2.0tie5454.8tie
Questions people ask
Which is better, GPT-5.2 or MAI-Code-1-Flash?
GPT-5.2 wins three of the four areas where both have results: coding, reasoning and math. MAI-Code-1-Flash wins none. They are level on following instructions.
Which is better for coding?
GPT-5.2. It wins 2 of the 3 coding tests both models report; MAI-Code-1-Flash wins 1.
How do you compare the two?
We use the 9 benchmark tests both models have published scores on. The verdict counts the 7 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 2 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.