GPT-5.6 Sol vs GPT-6 Luna
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 0 of 8 areas
—
GPT-5.6 Sol is the stronger all-rounder.GPT-6 Luna is cheaper.
Scores updated · 39 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.
- ReasoningHard problems that need careful thinking50GPT-5.6 Sol5 of 5 tests
- CodingWriting and fixing software40GPT-5.6 Sol4 of 4 tests
- MathCompetition and research-level math30GPT-5.6 Sol3 of 3 tests
- AgentsCarrying out multi-step tasks on its own20GPT-5.6 Sol2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-5.6 Sol2 of 2 tests
- FactsGetting facts right instead of making them up21GPT-5.6 Sol2 of 3 tests
- Following instructionsDoing exactly what it is asked10GPT-5.6 Sol1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
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.
GPT-6 Luna costs 98% 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-5.6 Sol pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+33.2points ahead
- Short factual questions, answered correctlySimpleQA Verified+28.3points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+27.3points ahead
Where GPT-6 Luna pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+15.5points ahead
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-5.6 Sol
- LiveBench · Agentic CodingGPT-5.6 Sol by 556.251.2+5
- LiveBench · CodingGPT-5.6 Sol by 4.983.979+4.9
- LMArena · WebDevGPT-5.6 Sol by 38 rating points16151577+38 rating
- SciCodeGPT-5.6 Sol by 2.557.154.6+2.5
AgentsGPT-5.6 Sol
- Terminal-Bench 4.0GPT-5.6 Sol by 27.339.912.6+27.3
- GDPValGPT-5.6 Sol by 8.855.446.6+8.8
ReasoningGPT-5.6 Sol
- ARC-AGI-2GPT-5.6 Sol by 33.292.559.3+33.2
- CritPtGPT-5.6 Sol by 12.932.319.4+12.9
- Humanity's Last ExamGPT-5.6 Sol by 1149.538.5+11
- LiveBench · ReasoningGPT-5.6 Sol by 9.991.781.8+9.9
- ARC-AGI-3GPT-5.6 Sol by 7.77.80.1+7.7
FactsGPT-5.6 Sol
- SimpleQA VerifiedGPT-5.6 Sol by 28.369.741.4+28.3
- AA-Omniscience · AccuracyGPT-5.6 Sol by 15.659.443.8+15.6
- AA-Omniscience · Non-hallucinationGPT-6 Luna by 15.57.823.3+15.5
Images and chartsGPT-5.6 Sol
- LMArena · VisionGPT-5.6 Sol by 71 rating points12821211+71 rating
- MMMU-ProGPT-5.6 Sol by 3.783.479.7+3.7
MathGPT-5.6 Sol
- FrontierMath Tier 4GPT-5.6 Sol by 26.98356.1+26.9
- FrontierMath Tiers 1-3 (v2)GPT-5.6 Sol by 10.189.179+10.1
- LiveBench · MathematicsGPT-5.6 Sol by 7.196.289.1+7.1
Following instructionsGPT-5.6 Sol
- LiveBench · Instruction FollowingGPT-5.6 Sol by 1671.855.9+16
Other results18 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 21.3220.7+21.3
- Terminal-Bench 4.0GPT-5.6 Sol by 20.937.316.4+20.9
- GDPval-AA 2.1GPT-5.6 Sol by 151 rating points15881437+151 rating
- livebench_languageGPT-5.6 Sol by 13.987.773.8+13.9
- Terminal-Bench-Science 0.1GPT-5.6 Sol by 13.822.48.6+13.8
- OSWorld 2.0GPT-5.6 Sol by 9.962.652.7+9.9
- ARC-AGI-1GPT-5.6 Sol by 9.896.586.7+9.8
- AA IntelligenceGPT-5.6 Sol by 8.94738.1+8.9
- GDP (Surge AI)GPT-5.6 Sol by 7.930.722.8+7.9
- DeepSWE 1.1GPT-5.6 Sol by 6.47366.6+6.4
- livebench_data_analysisGPT-5.6 Sol by 6.479.873.4+6.4
- HealthBench length-adjustedGPT-5.6 Sol by 2.55754.5+2.5
- HealthBenchGPT-5.6 Sol by 2.45754.6+2.4
- Agents' Last ExamGPT-5.6 Sol by 1.852.750.9+1.8
- HealthBench Hard length-adjustedGPT-5.6 Sol by 1.733.131.4+1.7
- HealthBench ProfessionalGPT-6 Luna by 1.460.561.9+1.4
- HealthBench Consensus length-adjustedtie95.595.9tie
- HealthBench Professional length-adjustedtie60.560.8tie
Questions people ask
Which is better, GPT-5.6 Sol or GPT-6 Luna?
GPT-5.6 Sol wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. GPT-6 Luna wins none, but costs 98% less. They are level on long documents.
Which is better for coding?
GPT-5.6 Sol. It wins 4 of the 4 coding tests both models report; GPT-6 Luna wins none.
Which is cheaper?
GPT-5.6 Sol costs $4.00 per million input tokens and $20.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. That makes GPT-6 Luna about 98% cheaper for the same work.
How do you compare the two?
We use the 39 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 18 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.