GPT-6 Astra vs GPT-6 Luna
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
Wins 1 of 8 areas
Long documents
GPT-6 Astra is the stronger all-rounder.GPT-6 Luna is cheaper and better at long documents.
Scores updated · 41 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-6 Astra5 of 5 tests
- CodingWriting and fixing software40GPT-6 Astra4 of 4 tests
- FactsGetting facts right instead of making them up30GPT-6 Astra3 of 3 tests
- MathCompetition and research-level math30GPT-6 Astra3 of 3 tests
- AgentsCarrying out multi-step tasks on its own20GPT-6 Astra2 of 2 tests
- Images and chartsUnderstanding pictures, charts and video20GPT-6 Astra2 of 2 tests
- Following instructionsDoing exactly what it is asked10GPT-6 Astra1 of 1 test
- Long documentsFinding answers in very long texts01GPT-6 Luna1 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.
GPT-6 Luna costs 99% 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-6 Astra pulls ahead
- Solves new puzzle games it has never seenARC-AGI-3+99.8points ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+46.5points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+41.5points ahead
Where GPT-6 Luna pulls ahead
- Reasons across sets of long documentsAA-LCR+2.6points ahead
Every test, side by side
All 41 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-6 Astra
- LMArena · WebDevGPT-6 Astra by 187 rating points17641577+187 rating
- LiveBench · Agentic CodingGPT-6 Astra by 6.157.351.2+6.1
- SciCodeGPT-6 Astra by 1.956.554.6+1.9
- LiveBench · CodingGPT-6 Astra by 1.480.479+1.4
AgentsGPT-6 Astra
- Terminal-Bench 4.0GPT-6 Astra by 46.559.112.6+46.5
- GDPValGPT-6 Astra by 753.646.6+7
ReasoningGPT-6 Astra
- ARC-AGI-3GPT-6 Astra by 99.899.90.1+99.8
- ARC-AGI-2GPT-6 Astra by 35.79559.3+35.7
- Humanity's Last ExamGPT-6 Astra by 16.254.738.5+16.2
- CritPtGPT-6 Astra by 12.331.719.4+12.3
- LiveBench · ReasoningGPT-6 Astra by 10.992.781.8+10.9
FactsGPT-6 Astra
- SimpleQA VerifiedGPT-6 Astra by 34.275.641.4+34.2
- AA-Omniscience · Non-hallucinationGPT-6 Astra by 25.448.723.3+25.4
- AA-Omniscience · AccuracyGPT-6 Astra by 18.862.643.8+18.8
Images and chartsGPT-6 Astra
- MMMU-ProGPT-6 Astra by 7.286.979.7+7.2
- LMArena · VisionGPT-6 Astra by 68 rating points12791211+68 rating
MathGPT-6 Astra
- FrontierMath Tier 4GPT-6 Astra by 41.597.656.1+41.5
- FrontierMath Tiers 1-3 (v2)GPT-6 Astra by 14.793.779+14.7
- LiveBench · MathematicsGPT-6 Astra by 7.796.889.1+7.7
Following instructionsGPT-6 Astra
- LiveBench · Instruction FollowingGPT-6 Astra by 19.775.655.9+19.7
Other results20 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.
- Terminal-Bench-Science 0.1GPT-6 Astra by 54.763.38.6+54.7
- AA-OmniscienceGPT-6 Astra by 42.743.40.7+42.7
- HLE-DiamondGPT-6 Astra by 41.663.822.2+41.6
- Terminal-Bench 4.0GPT-6 Astra by 41.357.716.4+41.3
- CritPt v2 HardGPT-6 Astra by 2870.542.5+28
- OSWorld 2.0GPT-6 Astra by 19.972.652.7+19.9
- livebench_languageGPT-6 Astra by 15.689.473.8+15.6
- AA IntelligenceGPT-6 Astra by 14.652.738.1+14.6
- ARC-AGI-1GPT-6 Astra by 10.897.586.7+10.8
- GDPval-AA 2.1GPT-6 Astra by 105 rating points15421437+105 rating
- livebench_data_analysisGPT-6 Astra by 9.68373.4+9.6
- Agents' Last ExamGPT-6 Astra by 8.459.350.9+8.4
- GDP (Surge AI)GPT-6 Astra by 8.23122.8+8.2
- DeepSWE 1.1GPT-6 Astra by 7.574.166.6+7.5
- HealthBench Hard length-adjustedGPT-6 Astra by 5.236.631.4+5.2
- HealthBench ProfessionalGPT-6 Astra by 4.16661.9+4.1
- HealthBench Professional length-adjustedGPT-6 Astra by 3.964.760.8+3.9
- HealthBench length-adjustedGPT-6 Astra by 3.858.354.5+3.8
- HealthBenchGPT-6 Astra by 3.658.254.6+3.6
- HealthBench Consensus length-adjustedtie95.595.9tie
Questions people ask
Which is better, GPT-6 Astra or GPT-6 Luna?
GPT-6 Astra wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. GPT-6 Luna wins long documents, and costs 99% less.
Which is better for coding?
GPT-6 Astra. It wins 4 of the 4 coding tests both models report; GPT-6 Luna wins none.
Which is cheaper?
GPT-6 Astra costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. That makes GPT-6 Luna about 99% cheaper for the same work.
How do you compare the two?
We use the 41 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 20 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.