GPT-5.6 Sol vs Step 5 Preview
Wins 3 of 6 areas
Agents · Reasoning · Images and charts
Wins 1 of 6 areas
Long documents
GPT-5.6 Sol wins more areas, narrowly.Step 5 Preview is cheaper and better at long documents.
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 own30GPT-5.6 Sol3 of 4 tests · 1 tie
- ReasoningHard problems that need careful thinking20GPT-5.6 Sol2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-5.6 Sol2 of 2 tests
- Long documentsFinding answers in very long texts01Step 5 Preview1 of 1 test
- CodingWriting and fixing software11Even1 each
- 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 85% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where GPT-5.6 Sol pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+17.9points ahead
- Research-level physics problemsCritPt+11.4points ahead
- Harder college exam questions with imagesMMMU-Pro+7points ahead
Where Step 5 Preview pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+49.2points ahead
- Reasons across sets of long documentsAA-LCR+4.3points ahead
- Code for real scientific research problemsSciCode+1.8points 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.
CodingEven
- LMArena · WebDevGPT-5.6 Sol by 45 rating points16161571+45 rating
- SciCodeStep 5 Preview by 1.857.158.9+1.8
AgentsGPT-5.6 Sol
- Terminal-Bench 4.0GPT-5.6 Sol by 6.639.933.3+6.6
- AA ApexAgentsGPT-5.6 Sol by 1.939.938+1.9
- GDPValGPT-5.6 Sol by 1.155.454.3+1.1
- AA IT-Bench SREtie56.255.6tie
ReasoningGPT-5.6 Sol
- CritPtGPT-5.6 Sol by 11.432.320.9+11.4
- Humanity's Last ExamGPT-5.6 Sol by 349.546.5+3
FactsEven
- AA-Omniscience · Non-hallucinationStep 5 Preview by 49.27.857+49.2
- AA-Omniscience · AccuracyGPT-5.6 Sol by 17.959.441.5+17.9
Images and chartsGPT-5.6 Sol
- MMMU-ProGPT-5.6 Sol by 783.476.4+7
- LMArena · VisionGPT-5.6 Sol by 16 rating points12811265+16 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-OmniscienceGPT-5.6 Sol by 5.62216.4+5.6
- AA IntelligenceGPT-5.6 Sol by 3.34743.7+3.3
Questions people ask
Which is better, GPT-5.6 Sol or Step 5 Preview?
GPT-5.6 Sol wins three of the six areas where both have results: agents, reasoning and images and charts. Step 5 Preview wins long documents, and costs 85% less. They are level on coding and facts.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
Which is cheaper?
GPT-5.6 Sol costs $4.00 per million input tokens and $20.00 per million output tokens; Step 5 Preview costs $1.00 and $2.70. That makes Step 5 Preview about 85% 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.