Claude Opus 4.6 is the stronger all-rounder.GPT-5.2 Pro is better at math.
Scores updated · 10 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 4.6 costs 84% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Opus 4.6 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+14.6points ahead
- Common-sense trick questionsSimpleBench+10.2points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+6.1points ahead
Where GPT-5.2 Pro pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+19.2points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+8points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.6points ahead
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningClaude Opus 4.6
- ARC-AGI-2Claude Opus 4.6 by 14.668.854.2+14.6
- SimpleBenchClaude Opus 4.6 by 10.267.657.4+10.2
- GPQA DiamondGPT-5.2 Pro by 3.689.693.2+3.6
- Humanity's Last ExamClaude Opus 4.6 by 3.339.936.6+3.3
MathGPT-5.2 Pro
- FrontierMath Tier 4GPT-5.2 Pro by 19.226.846+19.2
- FrontierMath Tiers 1-3 (v2)GPT-5.2 Pro by 86674+8
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 8.422.931.3+8.4
- ARC-AGI-1Claude Opus 4.6 by 2.59390.5+2.5
- AIME 2025tie99.8100tie
Questions people ask
Which is better, Claude Opus 4.6 or GPT-5.2 Pro?
Claude Opus 4.6 wins two of the three areas where both have results: agents and reasoning. GPT-5.2 Pro wins math.
Which is cheaper?
Claude Opus 4.6 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 4.6 about 84% cheaper for the same work.
How do you compare the two?
We use the 10 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 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.