GPT-5.4 mini vs Step 5 Preview
Wins 0 of 6 areas
—
Wins 6 of 6 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Step 5 Preview is the stronger all-rounder.
Scores updated · 15 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- AgentsCarrying out multi-step tasks on its own04Step 5 Preview4 of 4 tests
- CodingWriting and fixing software02Step 5 Preview2 of 2 tests
- ReasoningHard problems that need careful thinking02Step 5 Preview2 of 2 tests
- FactsGetting facts right instead of making them up02Step 5 Preview2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video02Step 5 Preview2 of 2 tests
- Long documentsFinding answers in very long texts01Step 5 Preview1 of 1 test
Long documents 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.
Step 5 Preview costs 30% 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 Step 5 Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+47.2points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+31.3points ahead
- Real work tasks from 44 professionsGDPVal+28.7points ahead
Where GPT-5.4 mini pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingStep 5 Preview
- LMArena · WebDevStep 5 Preview by 174 rating points13971571+174 rating
- SciCodeStep 5 Preview by 6.852.158.9+6.8
AgentsStep 5 Preview
- Terminal-Bench 4.0Step 5 Preview by 31.3233.3+31.3
- GDPValStep 5 Preview by 28.725.654.3+28.7
- AA IT-Bench SREStep 5 Preview by 20.435.255.6+20.4
- AA ApexAgentsStep 5 Preview by 9.828.238+9.8
ReasoningStep 5 Preview
- Humanity's Last ExamStep 5 Preview by 18.428.146.5+18.4
- CritPtStep 5 Preview by 10.91020.9+10.9
FactsStep 5 Preview
- AA-Omniscience · Non-hallucinationStep 5 Preview by 47.29.857+47.2
- AA-Omniscience · AccuracyStep 5 Preview by 437.541.5+4
Images and chartsStep 5 Preview
- MMMU-ProStep 5 Preview by 3.173.376.4+3.1
- LMArena · VisionStep 5 Preview by 20 rating points12451265+20 rating
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.
- AA-OmniscienceStep 5 Preview by 35.3-18.916.4+35.3
- AA IntelligenceStep 5 Preview by 19.624.143.7+19.6
Questions people ask
Which is better, GPT-5.4 mini or Step 5 Preview?
Step 5 Preview wins all six areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. GPT-5.4 mini wins none.
Which is better for coding?
Step 5 Preview. It wins 2 of the 2 coding tests both models report; GPT-5.4 mini wins none.
Which is cheaper?
GPT-5.4 mini costs $0.75 per million input tokens and $4.50 per million output tokens; Step 5 Preview costs $1.00 and $2.70. That makes Step 5 Preview about 30% cheaper for the same work.
How do you compare the two?
We use the 15 benchmark tests both models have published scores on. The verdict counts the 13 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.