GPT-5 vs GPT-6 Astra
Wins 0 of 7 areas
—
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
GPT-6 Astra is the stronger all-rounder.GPT-5 is cheaper.
Scores updated · 33 tests both models report · How we compare
Where each one wins
Tests won in each of the seven 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.
- ReasoningHard problems that need careful thinking05GPT-6 Astra5 of 5 tests
- FactsGetting facts right instead of making them up04GPT-6 Astra4 of 4 tests
- CodingWriting and fixing software03GPT-6 Astra3 of 3 tests
- AgentsCarrying out multi-step tasks on its own03GPT-6 Astra3 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02GPT-6 Astra2 of 2 tests
- MathCompetition and research-level math02GPT-6 Astra2 of 2 tests
- Long documentsFinding answers in very long texts01GPT-6 Astra1 of 1 test
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.
GPT-5 costs 81% 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
- Abstract visual puzzles that people can solveARC-AGI-2+85.1points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+75.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+53.2points ahead
Where GPT-5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-6 Astra
- Terminal-Bench 2.1GPT-6 Astra by 53.235.288.4+53.2
- LMArena · WebDevGPT-6 Astra by 357 rating points14181775+357 rating
- SciCodeGPT-6 Astra by 13.642.956.5+13.6
AgentsGPT-6 Astra
- BrowseCompGPT-6 Astra by 36.654.991.5+36.6
- GDPValGPT-6 Astra by 32.720.953.6+32.7
- τ-Bench V3 · BankingGPT-6 Astra by 19.322.141.4+19.3
ReasoningGPT-6 Astra
- ARC-AGI-2GPT-6 Astra by 85.19.995+85.1
- SimpleBenchGPT-6 Astra by 26.956.783.6+26.9
- Humanity's Last ExamGPT-6 Astra by 26.228.554.7+26.2
- CritPtGPT-6 Astra by 265.731.7+26
- GPQA DiamondGPT-6 Astra by 10.785.496.1+10.7
FactsGPT-6 Astra
- AA-Omniscience · Non-hallucinationGPT-6 Astra by 30.917.848.7+30.9
- SimpleQA VerifiedGPT-6 Astra by 25.550.175.6+25.5
- AA-Omniscience · AccuracyGPT-6 Astra by 22.340.362.6+22.3
- Vectara HHEM hallucination ratelower is betterGPT-6 Astra by 6.415.18.7+6.4
Images and chartsGPT-6 Astra
- MMMU-ProGPT-6 Astra by 12.774.286.9+12.7
- LMArena · VisionGPT-6 Astra by 72 rating points12081280+72 rating
MathGPT-6 Astra
- FrontierMath Tier 4GPT-6 Astra by 75.621.997.6+75.6
- FrontierMath Tiers 1-3 (v2)GPT-6 Astra by 38.355.493.7+38.3
Other results13 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-6 Astra by 52.1-8.743.4+52.1
- Artificial Analysis Coding IndexGPT-6 Astra by 39.137.876.9+39.1
- ARC-AGI-1GPT-6 Astra by 31.865.797.5+31.8
- AA IntelligenceGPT-6 Astra by 29.72352.7+29.7
- AA Agentic IndexGPT-6 Astra by 2526.551.5+25
- HLE (with tools)GPT-6 Astra by 2235.257.2+22
- HealthBench Professional length-adjustedGPT-6 Astra by 18.546.264.7+18.5
- vectara_factual_consistencyGPT-6 Astra by 6.484.991.3+6.4
- HealthBench Hard length-adjustedGPT-6 Astra by 1.934.736.6+1.9
- vectara_avg_summary_lengthGPT-5 by 14.2 rating points162.7148.5+14.2 rating
- HealthBench length-adjustedtie57.758.3tie
- HealthBench Consensus length-adjustedtie95.695.5tie
- vectara_answer_ratetie99.9100tie
Questions people ask
Which is better, GPT-5 or GPT-6 Astra?
GPT-6 Astra wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, math and long documents. GPT-5 wins none, but costs 81% less.
Which is better for coding?
GPT-6 Astra. It wins 3 of the 3 coding tests both models report; GPT-5 wins none.
Which is cheaper?
GPT-5 costs $1.25 per million input tokens and $10.00 per million output tokens; GPT-6 Astra costs $10.00 and $50.00. That makes GPT-5 about 81% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 13 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.