Claude Sonnet 4 vs Claude Sonnet 4.6
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Images and charts · Long documents · Following instructions
Claude Sonnet 4.6 is the stronger all-rounder.
Scores updated · 34 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.
- CodingWriting and fixing software05Claude Sonnet 4.65 of 5 tests
- AgentsCarrying out multi-step tasks on its own04Claude Sonnet 4.64 of 4 tests
- ReasoningHard problems that need careful thinking04Claude Sonnet 4.64 of 4 tests
- Images and chartsUnderstanding pictures, charts and video02Claude Sonnet 4.62 of 2 tests
- Long documentsFinding answers in very long texts01Claude Sonnet 4.61 of 1 test
- Following instructionsDoing exactly what it is asked01Claude Sonnet 4.61 of 1 test
- FactsGetting facts right instead of making them up11Even1 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Claude Sonnet 4.6 pulls ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+62.5points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+52.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+34.9points ahead
Where Claude Sonnet 4 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+19.3points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- Terminal-Bench 2.1Claude Sonnet 4.6 by 34.936.371.2+34.9
- Terminal-Bench HardClaude Sonnet 4.6 by 21.931.153+21.9
- SWE-bench ProClaude Sonnet 4.6 by 15.442.758.1+15.4
- SciCodeClaude Sonnet 4.6 by 10.14050.1+10.1
- SWE-bench VerifiedClaude Sonnet 4.6 by 6.972.779.6+6.9
AgentsClaude Sonnet 4.6
- BrowseCompClaude Sonnet 4.6 by 62.512.274.7+62.5
- OSWorld-VerifiedClaude Sonnet 4.6 by 30.342.272.5+30.3
- GDPValClaude Sonnet 4.6 by 279.636.6+27
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 17.716.734.4+17.7
ReasoningClaude Sonnet 4.6
- ARC-AGI-2Claude Sonnet 4.6 by 52.45.958.3+52.4
- Humanity's Last ExamClaude Sonnet 4.6 by 22.910.733.6+22.9
- GPQA DiamondClaude Sonnet 4.6 by 9.877.787.5+9.8
- CritPtClaude Sonnet 4.6 by 2.80.33.1+2.8
FactsEven
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 19.370.951.6+19.3
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 18.222.740.9+18.2
- Vectara HHEM hallucination ratelower is bettertie10.310.6tie
Images and chartsClaude Sonnet 4.6
- MMMU-ProClaude Sonnet 4.6 by 11.561.873.3+11.5
- LMArena · VisionClaude Sonnet 4.6 by 92 rating points11911283+92 rating
Following instructionsClaude Sonnet 4.6
- IFBenchClaude Sonnet 4.6 by 1.954.756.6+1.9
Other results14 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.
- ARC-AGI-1Claude Sonnet 4.6 by 464086+46
- HLE (with tools)Claude Sonnet 4.6 by 26.520.346.8+26.5
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 25.437.663+25.4
- τ²-Bench (Retail)Claude Sonnet 4.6 by 16.77591.7+16.7
- AA Agentic IndexClaude Sonnet 4.6 by 15.517.633.1+15.5
- AA-OmniscienceClaude Sonnet 4.6 by 120.212.2+12
- AA IntelligenceClaude Sonnet 4.6 by 11.218.930.1+11.2
- τ²-Bench Telecom (AA run)Claude Sonnet 4.6 by 11.164.675.7+11.1
- frontiermath_tier_4_v1Claude Sonnet 4.6 by 8.308.3+8.3
- vectara_avg_summary_lengthClaude Sonnet 4 by 31.1 rating points145.8114.7+31.1 rating
- MMMLUClaude Sonnet 4.6 by 2.886.589.3+2.8
- vectara_answer_rateClaude Sonnet 4.6 by 1.398.699.9+1.3
- LiveBenchtie74.875.5tie
- vectara_factual_consistencytie89.789.4tie
Questions people ask
Which is better, Claude Sonnet 4 or Claude Sonnet 4.6?
Claude Sonnet 4.6 wins six of the seven areas where both have results: coding, agents, reasoning, images and charts, long documents and following instructions. Claude Sonnet 4 wins none. They are level on facts.
Which is better for coding?
Claude Sonnet 4.6. It wins 5 of the 5 coding tests both models report; Claude Sonnet 4 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Sonnet 4.6 costs $3.00 and $15.00. For a million tokens read plus a million written, they cost about the same.
How do you compare the two?
We use the 34 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 14 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.