Gemini 4 Argon vs GPT-6 Astra
Wins 0 of 6 areas
—
Wins 4 of 6 areas
Reasoning · Facts · Math · Long documents
GPT-6 Astra is the stronger all-rounder.Gemini 4 Argon is cheaper.
Both rank among the ten best models we track in facts.
Scores updated · 45 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.
- ReasoningHard problems that need careful thinking13GPT-6 Astra3 of 4 tests
- MathCompetition and research-level math02GPT-6 Astra2 of 2 tests
- FactsGetting facts right instead of making them up12GPT-6 Astra2 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts01GPT-6 Astra1 of 1 test
- CodingWriting and fixing software11Even1 each
- AgentsCarrying out multi-step tasks on its own11Even1 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.
Gemini 4 Argon costs 80% 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-6 Astra pulls ahead
- Solves new puzzle games it has never seenARC-AGI-3+53.6points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+19.5points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+12.7points ahead
Where Gemini 4 Argon pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+36.2points ahead
- Code for real scientific research problemsSciCode+5.3points ahead
- Real work tasks from 44 professionsGDPVal+2.6points ahead
Every test, side by side
All 45 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- LMArena · WebDevGPT-6 Astra by 98 rating points16781776+98 rating
- SciCodeGemini 4 Argon by 5.361.856.5+5.3
AgentsEven
- GDPValGemini 4 Argon by 2.656.253.6+2.6
- Terminal-Bench 4.0GPT-6 Astra by 257.159.1+2
ReasoningGPT-6 Astra
- ARC-AGI-3GPT-6 Astra by 53.646.399.9+53.6
- CritPtGPT-6 Astra by 4.627.131.7+4.6
- ARC-AGI-2GPT-6 Astra by 3.791.395+3.7
- Humanity's Last ExamGemini 4 Argon by 2.457.154.7+2.4
FactsGPT-6 Astra
- AA-Omniscience · Non-hallucinationGemini 4 Argon by 36.284.948.7+36.2
- AA-Omniscience · AccuracyGPT-6 Astra by 12.749.962.6+12.7
- Vectara HHEM hallucination ratelower is betterGPT-6 Astra by 3.412.18.7+3.4
- SimpleQA Verifiedtie7675.6tie
MathGPT-6 Astra
- FrontierMath Tier 4GPT-6 Astra by 19.57897.6+19.5
- FrontierMath Tiers 1-3 (v2)GPT-6 Astra by 7.78693.7+7.7
Other results30 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.
- Agents' Last ExamGPT-6 Astra by 19.839.559.3+19.8
- GraphWalks (256k to 1M, BFS (F1))Gemini 4 Argon by 12.484.271.8+12.4
- Science and math (Terminal-Bench Science 0.1)GPT-6 Astra by 10.557.668.1+10.5
- AutomationBench (Score)Gemini 4 Argon by 9.951.341.4+9.9
- Knowledge work (AutomationBench)Gemini 4 Argon by 9.951.341.4+9.9
- Terminal-Bench-Science 0.1GPT-6 Astra by 757.664.6+7
- Knowledge work (Vals Index)Gemini 4 Argon by 5.868.963.1+5.8
- Vals IndexGemini 4 Argon by 5.868.963.1+5.8
- Agent's Last Exam (Pass rate)Gemini 4 Argon by 5.339.534.2+5.3
- Computer use (Agent's Last Exam)Gemini 4 Argon by 5.339.534.2+5.3
- LVBenchGemini 4 Argon by 4.291.787.5+4.2
- Multimodal understanding (LVBench)Gemini 4 Argon by 4.291.787.5+4.2
- RiemannBenchGemini 4 Argon by 47672+4
- Science and math (RiemannBench)Gemini 4 Argon by 47672+4
- DeepSWE 1.1Gemini 4 Argon by 3.877.974.1+3.8
- Computer use (OSWorld-2.0)GPT-6 Astra by 3.469.272.6+3.4
- OSWorld 2.0GPT-6 Astra by 3.469.272.6+3.4
- OSWorld-2.0 (Offline subset)GPT-6 Astra by 3.469.272.6+3.4
- vectara_factual_consistencyGPT-6 Astra by 3.487.991.3+3.4
- HiL-Bench (Tools-allowed)GPT-6 Astra by 3.36265.3+3.3
- vectara_avg_summary_lengthGemini 4 Argon by 29.7 rating points178.2148.5+29.7 rating
- AA-OmniscienceGPT-6 Astra by 142.443.4+1
- ARC-AGI-1Gemini 4 Argon by 198.597.5+1
- GraphWalks (Up to 128k, BFS (F1))Gemini 4 Argon by 199.798.7+1
- PostTrainBenchGemini 4 Argon by 145.344.3+1
- vectara_answer_ratetie99.1100tie
- Agentic coding (Terminal-bench 4.0)tie57.458.2tie
- Terminal-Bench 4.0tie57.457.7tie
- AA Intelligencetie52.652.7tie
- Cybersecurity (CWE-bench v1)tie6868tie
Questions people ask
Which is better, Gemini 4 Argon or GPT-6 Astra?
GPT-6 Astra wins four of the six areas where both have results: reasoning, facts, math and long documents. Gemini 4 Argon wins none, but costs 80% less. They are level on coding and agents.
Which is better for coding?
Neither. They win 1 coding test each of the 2 both models report.
Which is cheaper?
Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6 Astra costs $10.00 and $50.00. That makes Gemini 4 Argon about 80% cheaper for the same work.
How do you compare the two?
We use the 45 benchmark tests both models have published scores on. The verdict counts the 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 30 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.