Claude Sonnet 4.5 vs GPT-5.4 Pro
Wins 0 of 5 areas
—
Wins 5 of 5 areas
Agents · Reasoning · Facts · Math · Following instructions
GPT-5.4 Pro is the stronger all-rounder.Claude Sonnet 4.5 is cheaper.
Scores updated · 16 tests both models report · How we compare
Where each one wins
Tests won in each of the five 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.
- ReasoningHard problems that need careful thinking04GPT-5.4 Pro4 of 4 tests
- FactsGetting facts right instead of making them up02GPT-5.4 Pro2 of 2 tests
- MathCompetition and research-level math02GPT-5.4 Pro2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01GPT-5.4 Pro1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-5.4 Pro1 of 1 test
Agents 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.
Claude Sonnet 4.5 costs 91% 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-5.4 Pro pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+69.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+65.2points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+58.6points ahead
Where Claude Sonnet 4.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningGPT-5.4 Pro
- ARC-AGI-2GPT-5.4 Pro by 69.713.683.3+69.7
- CritPtGPT-5.4 Pro by 28.91.130+28.9
- Humanity's Last ExamGPT-5.4 Pro by 24.917.842.7+24.9
- GPQA DiamondGPT-5.4 Pro by 1183.494.4+11
FactsGPT-5.4 Pro
- SimpleQA VerifiedGPT-5.4 Pro by 15.630.746.3+15.6
- Vectara HHEM hallucination ratelower is betterGPT-5.4 Pro by 3.7128.3+3.7
MathGPT-5.4 Pro
- FrontierMath Tiers 1-3 (v2)GPT-5.4 Pro by 58.623.982.5+58.6
- FrontierMath Tier 4GPT-5.4 Pro by 56.12.458.5+56.1
Following instructionsGPT-5.4 Pro
- Multi-ChallengeGPT-5.4 Pro by 13.955.369.2+13.9
Other results6 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-5.4 Pro by 33.34.237.5+33.3
- ARC-AGI-1GPT-5.4 Pro by 30.863.794.5+30.8
- HLE (with tools)GPT-5.4 Pro by 26.73258.7+26.7
- vectara_answer_rateGPT-5.4 Pro by 4.495.6100+4.4
- vectara_factual_consistencyGPT-5.4 Pro by 3.78891.7+3.7
- vectara_avg_summary_lengthGPT-5.4 Pro by 20.7 rating points127.8148.5+20.7 rating
Questions people ask
Which is better, Claude Sonnet 4.5 or GPT-5.4 Pro?
GPT-5.4 Pro wins all five areas where both have results: agents, reasoning, facts, math and following instructions. Claude Sonnet 4.5 wins none, but costs 91% less.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.4 Pro costs $30.00 and $180.00. That makes Claude Sonnet 4.5 about 91% cheaper for the same work.
How do you compare the two?
We use the 16 benchmark tests both models have published scores on. The verdict counts the 10 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 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.