GPT-5.5 vs Step 3.7 Flash
Wins 7 of 8 areas
Coding · Agents · Reasoning · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
GPT-5.5 is the stronger all-rounder.Step 3.7 Flash is cheaper.
Scores updated · 23 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software40GPT-5.54 of 4 tests
- AgentsCarrying out multi-step tasks on its own40GPT-5.54 of 4 tests
- ReasoningHard problems that need careful thinking30GPT-5.53 of 3 tests
- MathCompetition and research-level math20GPT-5.52 of 2 tests
- Images and chartsUnderstanding pictures, charts and video10GPT-5.51 of 1 test
- Long documentsFinding answers in very long texts10GPT-5.51 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.51 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Images and charts, long documents 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.
Step 3.7 Flash costs 96% 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-5.5 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+45points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+32.2points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+27points ahead
Where Step 3.7 Flash pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+4points ahead
Every test, side by side
All 23 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.5
- Terminal-Bench 2.1GPT-5.5 by 4584.339.3+45
- Terminal-Bench HardGPT-5.5 by 2560.635.6+25
- SciCodeGPT-5.5 by 11.955.843.9+11.9
- SWE-bench ProGPT-5.5 by 2.358.656.3+2.3
AgentsGPT-5.5
- τ-Bench V3 · BankingGPT-5.5 by 273912+27
- GDPValGPT-5.5 by 24.742.718+24.7
- AA ApexAgentsGPT-5.5 by 22.937.714.8+22.9
- AA IT-Bench SREGPT-5.5 by 15.545.830.3+15.5
ReasoningGPT-5.5
- CritPtGPT-5.5 by 24.827.12.3+24.8
- Humanity's Last ExamGPT-5.5 by 24.445.821.4+24.4
- GPQA DiamondGPT-5.5 by 12.693.580.9+12.6
FactsEven
- AA-Omniscience · AccuracyGPT-5.5 by 32.25825.8+32.2
- AA-Omniscience · Non-hallucinationStep 3.7 Flash by 41115+4
Other results5 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-OmniscienceGPT-5.5 by 57.820.5-37.3+57.8
- Artificial Analysis Coding IndexGPT-5.5 by 35.374.939.6+35.3
- AA IntelligenceGPT-5.5 by 18.938.419.5+18.9
- AA Agentic IndexGPT-5.5 by 15.637.321.7+15.6
- τ²-Bench Telecom (AA run)Step 3.7 Flash by 4.693.998.5+4.6
Questions people ask
Which is better, GPT-5.5 or Step 3.7 Flash?
GPT-5.5 wins seven of the eight areas we test: coding, agents, reasoning, images and charts, math, long documents and following instructions. Step 3.7 Flash wins none, but costs 96% less. They are level on facts.
Which is better for coding?
GPT-5.5. It wins 4 of the 4 coding tests both models report; Step 3.7 Flash wins none.
Which is cheaper?
GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. That makes Step 3.7 Flash about 96% cheaper for the same work.
How do you compare the two?
We use the 23 benchmark tests both models have published scores on. The verdict counts the 18 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 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.