GPT-5.5 vs GPT-5.5 Instant
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
GPT-5.5 is the stronger all-rounder.
Scores updated · 25 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 software30GPT-5.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own30GPT-5.53 of 3 tests
- ReasoningHard problems that need careful thinking30GPT-5.53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-5.52 of 2 tests
- MathCompetition and research-level math20GPT-5.52 of 2 tests
- FactsGetting facts right instead of making them up21GPT-5.52 of 3 tests
- Long documentsFinding answers in very long texts10GPT-5.51 of 1 test
- Following instructionsDoing exactly what it is asked10GPT-5.51 of 1 test
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.
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
- Extremely hard research-level math problemsFrontierMath Tier 4+70.1points ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+59points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+49.5points ahead
Where GPT-5.5 Instant pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+23.7points ahead
Every test, side by side
All 25 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 49.584.334.8+49.5
- Terminal-Bench HardGPT-5.5 by 18.260.642.4+18.2
- SciCodeGPT-5.5 by 3.355.852.5+3.3
AgentsGPT-5.5
- GDPValGPT-5.5 by 42.742.70+42.7
- τ-Bench V3 · BankingGPT-5.5 by 27.23911.8+27.2
- Terminal-Bench 4.0GPT-5.5 by 214.612.6+2
ReasoningGPT-5.5
- CritPtGPT-5.5 by 24.527.12.6+24.5
- Humanity's Last ExamGPT-5.5 by 24.245.821.6+24.2
- GPQA DiamondGPT-5.5 by 8.993.584.6+8.9
FactsGPT-5.5
- SimpleQA VerifiedGPT-5.5 by 256338+25
- AA-Omniscience · Non-hallucinationGPT-5.5 Instant by 23.71134.7+23.7
- AA-Omniscience · AccuracyGPT-5.5 by 11.75846.3+11.7
Images and chartsGPT-5.5
- LMArena · VisionGPT-5.5 by 42 rating points12921250+42 rating
- MMMU-ProGPT-5.5 by 3.979.976+3.9
MathGPT-5.5
- FrontierMath Tier 4GPT-5.5 by 70.172.52.4+70.1
- FrontierMath Tiers 1-3 (v2)GPT-5.5 by 5985.326.3+59
Other results7 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.
- τ²-Bench Telecom (AA run)GPT-5.5 by 44.593.949.4+44.5
- Artificial Analysis Coding IndexGPT-5.5 by 35.574.939.4+35.5
- AA Agentic IndexGPT-5.5 by 18.137.319.2+18.1
- AA IntelligenceGPT-5.5 by 15.738.422.7+15.7
- HealthBench ProfessionalGPT-5.5 by 13.451.838.4+13.4
- AA-OmniscienceGPT-5.5 by 9.320.511.2+9.3
- HealthBenchGPT-5.5 by 5.156.551.4+5.1
Questions people ask
Which is better, GPT-5.5 or GPT-5.5 Instant?
GPT-5.5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-5.5 Instant wins none.
Which is better for coding?
GPT-5.5. It wins 3 of the 3 coding tests both models report; GPT-5.5 Instant wins none.
Which is cheaper?
GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens; GPT-5.5 Instant costs $5.00 and $30.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 25 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 7 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.