GPT-5.2 Pro is the stronger all-rounder.Claude Opus 4.5 is cheaper.
Scores updated · 9 tests both models report · How we compare
Where each one wins
Tests won in each of the three 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.
Agents rests on a single test.
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.
Claude Opus 4.5 costs 84% less for the same work.
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 Pro pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+41.1points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+40.9points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+39.6points ahead
Where Claude Opus 4.5 pulls ahead
No clear win on a test scored out of 100.
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.
ReasoningGPT-5.2 Pro
- ARC-AGI-2GPT-5.2 Pro by 16.637.654.2+16.6
- GPQA DiamondGPT-5.2 Pro by 6.686.693.2+6.6
- Humanity's Last ExamGPT-5.2 Pro by 6.530.136.6+6.5
MathGPT-5.2 Pro
- FrontierMath Tier 4GPT-5.2 Pro by 41.14.946+41.1
- FrontierMath Tiers 1-3 (v2)GPT-5.2 Pro by 39.634.474+39.6
Other results3 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_tier_4_v1GPT-5.2 Pro by 27.14.231.3+27.1
- ARC-AGI-1GPT-5.2 Pro by 8.58290.5+8.5
- AIME 2025GPT-5.2 Pro by 7.292.8100+7.2
Questions people ask
Which is better, Claude Opus 4.5 or GPT-5.2 Pro?
GPT-5.2 Pro wins all three areas where both have results: agents, reasoning and math. Claude Opus 4.5 wins none, but costs 84% less.
Which is cheaper?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; GPT-5.2 Pro costs $21.00 and $168.00. That makes Claude Opus 4.5 about 84% cheaper for the same work.
How do you compare the two?
We use the 9 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 3 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.