GPT-5.5 vs Step 5 Preview
Wins 2 of 6 areas
Reasoning · Images and charts
Wins 3 of 6 areas
Coding · Agents · Long documents
Step 5 Preview wins more areas, narrowly.GPT-5.5 is better at images and charts.
Both rank among the ten best models we track in long documents.
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 own03Step 5 Preview3 of 4 tests · 1 tie
- CodingWriting and fixing software02Step 5 Preview2 of 2 tests
- Long documentsFinding answers in very long texts01Step 5 Preview1 of 1 test
- Images and chartsUnderstanding pictures, charts and video20GPT-5.52 of 2 tests
- ReasoningHard problems that need careful thinking10GPT-5.51 of 2 tests · 1 tie
- FactsGetting facts right instead of making them up11Even1 each
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 89% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Step 5 Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+46points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+18.7points ahead
- Real work tasks from 44 professionsGDPVal+11.8points ahead
Where GPT-5.5 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+16.5points ahead
- Research-level physics problemsCritPt+6.2points ahead
- Harder college exam questions with imagesMMMU-Pro+3.5points ahead
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 84 rating points14871571+84 rating
- SciCodeStep 5 Preview by 3.155.858.9+3.1
AgentsStep 5 Preview
- Terminal-Bench 4.0Step 5 Preview by 18.714.633.3+18.7
- GDPValStep 5 Preview by 11.842.554.3+11.8
- AA IT-Bench SREStep 5 Preview by 9.845.855.6+9.8
- AA ApexAgentstie37.738tie
ReasoningGPT-5.5
- CritPtGPT-5.5 by 6.227.120.9+6.2
- Humanity's Last Examtie45.846.5tie
FactsEven
- AA-Omniscience · Non-hallucinationStep 5 Preview by 461157+46
- AA-Omniscience · AccuracyGPT-5.5 by 16.55841.5+16.5
Images and chartsGPT-5.5
- MMMU-ProGPT-5.5 by 3.579.976.4+3.5
- LMArena · VisionGPT-5.5 by 28 rating points12931265+28 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 IntelligenceStep 5 Preview by 5.338.443.7+5.3
- AA-OmniscienceGPT-5.5 by 4.120.516.4+4.1
Questions people ask
Which is better, GPT-5.5 or Step 5 Preview?
Step 5 Preview wins three of the six areas where both have results: coding, agents and long documents. GPT-5.5 wins reasoning and images and charts. They are level on facts.
Which is better for coding?
Step 5 Preview. It wins 2 of the 2 coding tests both models report; GPT-5.5 wins none.
Which is cheaper?
GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens; Step 5 Preview costs $1.00 and $2.70. That makes Step 5 Preview about 89% 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.