Claude Sonnet 4.6 vs GPT-6 Astra
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Following instructions
GPT-6 Astra is the stronger all-rounder.Claude Sonnet 4.6 is cheaper.
Scores updated · 37 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 software05GPT-6 Astra5 of 5 tests
- AgentsCarrying out multi-step tasks on its own05GPT-6 Astra5 of 5 tests
- ReasoningHard problems that need careful thinking05GPT-6 Astra5 of 5 tests
- FactsGetting facts right instead of making them up13GPT-6 Astra3 of 4 tests
- Images and chartsUnderstanding pictures, charts and video01GPT-6 Astra1 of 2 tests · 1 tie
- MathCompetition and research-level math01GPT-6 Astra1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-6 Astra1 of 1 test
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Math, 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.
Claude Sonnet 4.6 costs 70% 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
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+56.1points ahead
- Short factual questions, answered correctlySimpleQA Verified+42.8points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+36.7points ahead
Where Claude Sonnet 4.6 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+2.9points ahead
Every test, side by side
All 37 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 252 rating points15231775+252 rating
- Terminal-Bench 2.1GPT-6 Astra by 17.271.288.4+17.2
- LiveBench · Agentic CodingGPT-6 Astra by 14.742.657.3+14.7
- SciCodeGPT-6 Astra by 6.450.156.5+6.4
- LiveBench · CodingGPT-6 Astra by 1.179.380.4+1.1
AgentsGPT-6 Astra
- Terminal-Bench 4.0GPT-6 Astra by 56.1359.1+56.1
- GDPValGPT-6 Astra by 1736.653.6+17
- BrowseCompGPT-6 Astra by 16.874.791.5+16.8
- AA IT-Bench SREGPT-6 Astra by 8.839.848.6+8.8
- τ-Bench V3 · BankingGPT-6 Astra by 734.441.4+7
ReasoningGPT-6 Astra
- ARC-AGI-2GPT-6 Astra by 36.758.395+36.7
- CritPtGPT-6 Astra by 28.63.131.7+28.6
- Humanity's Last ExamGPT-6 Astra by 21.133.654.7+21.1
- GPQA DiamondGPT-6 Astra by 8.687.596.1+8.6
- LiveBench · ReasoningGPT-6 Astra by 7.984.892.7+7.9
FactsGPT-6 Astra
- SimpleQA VerifiedGPT-6 Astra by 42.832.875.6+42.8
- AA-Omniscience · AccuracyGPT-6 Astra by 21.740.962.6+21.7
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 2.951.648.7+2.9
- Vectara HHEM hallucination ratelower is betterGPT-6 Astra by 1.910.68.7+1.9
Images and chartsGPT-6 Astra
- MMMU-ProGPT-6 Astra by 13.673.386.9+13.6
- LMArena · Visiontie12831280tie
Following instructionsGPT-6 Astra
- LiveBench · Instruction FollowingGPT-6 Astra by 12.463.275.6+12.4
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.
- DeepSWE 1.1GPT-6 Astra by 44.13074.1+44.1
- AA-OmniscienceGPT-6 Astra by 31.212.243.4+31.2
- AA IntelligenceGPT-6 Astra by 22.630.152.7+22.6
- HealthBench ProfessionalGPT-6 Astra by 19.244.263.4+19.2
- AA Agentic IndexGPT-6 Astra by 18.433.151.5+18.4
- Artificial Analysis Coding IndexGPT-6 Astra by 13.96376.9+13.9
- livebench_languageGPT-6 Astra by 13.376.189.4+13.3
- ARC-AGI-1GPT-6 Astra by 11.58697.5+11.5
- HLE (with tools)GPT-6 Astra by 10.446.857.2+10.4
- livebench_data_analysisGPT-6 Astra by 57883+5
- vectara_avg_summary_lengthGPT-6 Astra by 33.8 rating points114.7148.5+33.8 rating
- vectara_factual_consistencyGPT-6 Astra by 1.989.491.3+1.9
- vectara_answer_ratetie99.9100tie
Questions people ask
Which is better, Claude Sonnet 4.6 or GPT-6 Astra?
GPT-6 Astra wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and following instructions. Claude Sonnet 4.6 wins none, but costs 70% less. They are level on long documents.
Which is better for coding?
GPT-6 Astra. It wins 5 of the 5 coding tests both models report; Claude Sonnet 4.6 wins none.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-6 Astra costs $10.00 and $50.00. That makes Claude Sonnet 4.6 about 70% cheaper for the same work.
How do you compare the two?
We use the 37 benchmark tests both models have published scores on. The verdict counts the 24 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.