Claude Sonnet 4.5 vs Claude Sonnet 4.6
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents
Claude Sonnet 4.6 is the stronger all-rounder.
Scores updated · 42 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 software06Claude Sonnet 4.66 of 6 tests
- AgentsCarrying out multi-step tasks on its own06Claude Sonnet 4.66 of 6 tests
- ReasoningHard problems that need careful thinking04Claude Sonnet 4.64 of 4 tests
- FactsGetting facts right instead of making them up03Claude Sonnet 4.63 of 4 tests · 1 tie
- 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 asked00Even0 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+50.6points ahead
- Abstract visual puzzles that people can solveARC-AGI-2+44.7points ahead
- Multi-step tasks using many real software toolsMCP Atlas+17.5points ahead
Where Claude Sonnet 4.5 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 42 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- Terminal-Bench HardClaude Sonnet 4.6 by 17.435.653+17.4
- Terminal-Bench 2.1Claude Sonnet 4.6 by 15.455.871.2+15.4
- SWE-bench ProClaude Sonnet 4.6 by 14.543.658.1+14.5
- LMArena · WebDevClaude Sonnet 4.6 by 128 rating points13931521+128 rating
- SciCodeClaude Sonnet 4.6 by 4.445.750.1+4.4
- SWE-bench VerifiedClaude Sonnet 4.6 by 2.477.279.6+2.4
AgentsClaude Sonnet 4.6
- BrowseCompClaude Sonnet 4.6 by 50.624.174.7+50.6
- MCP AtlasClaude Sonnet 4.6 by 17.543.861.3+17.5
- GDPValClaude Sonnet 4.6 by 16.220.536.7+16.2
- OSWorld-VerifiedClaude Sonnet 4.6 by 11.161.472.5+11.1
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 9.924.534.4+9.9
- Terminal-Bench 4.0Claude Sonnet 4.6 by 303+3
ReasoningClaude Sonnet 4.6
- ARC-AGI-2Claude Sonnet 4.6 by 44.713.658.3+44.7
- Humanity's Last ExamClaude Sonnet 4.6 by 15.817.833.6+15.8
- GPQA DiamondClaude Sonnet 4.6 by 4.183.487.5+4.1
- CritPtClaude Sonnet 4.6 by 21.13.1+2
FactsClaude Sonnet 4.6
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 832.940.9+8
- SimpleQA VerifiedClaude Sonnet 4.6 by 2.130.732.8+2.1
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4.6 by 1.41210.6+1.4
- AA-Omniscience · Non-hallucinationtie50.951.6tie
Images and chartsClaude Sonnet 4.6
- MMMU-ProClaude Sonnet 4.6 by 4.668.773.3+4.6
- CharXiv (RQ)Claude Sonnet 4.6 by 4.467.271.6+4.4
Other results18 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 22.363.786+22.3
- AA Agentic IndexClaude Sonnet 4.6 by 15.617.533.1+15.6
- Toolathlon Avg turnsClaude Sonnet 4.5 by 15.53216.5+15.5
- HLE (with tools)Claude Sonnet 4.6 by 14.83246.8+14.8
- AA-OmniscienceClaude Sonnet 4.6 by 12.3-0.112.2+12.3
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 10.952.163+10.9
- AA IntelligenceClaude Sonnet 4.6 by 9.420.730.1+9.4
- Toolathlon Pass@∞Claude Sonnet 4.6 by 9.328.738+9.3
- Terminal-Bench 2.0Claude Sonnet 4.6 by 9.15059.1+9.1
- GPQA (unspecified)Claude Sonnet 4.6 by 6.583.489.9+6.5
- τ²-Bench (Retail)Claude Sonnet 4.6 by 5.586.291.7+5.5
- vectara_answer_rateClaude Sonnet 4.6 by 4.395.699.9+4.3
- frontiermath_tier_4_v1Claude Sonnet 4.6 by 4.14.28.3+4.1
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 2.478.175.7+2.4
- vectara_factual_consistencyClaude Sonnet 4.6 by 1.48889.4+1.4
- vectara_avg_summary_lengthClaude Sonnet 4.5 by 13.1 rating points127.8114.7+13.1 rating
- MMMLUtie89.189.3tie
- Toolathlontie4141tie
Questions people ask
Which is better, Claude Sonnet 4.5 or Claude Sonnet 4.6?
Claude Sonnet 4.6 wins six of the seven areas where both have results: coding, agents, reasoning, facts, images and charts and long documents. Claude Sonnet 4.5 wins none. They are level on following instructions.
Which is better for coding?
Claude Sonnet 4.6. It wins 6 of the 6 coding tests both models report; Claude Sonnet 4.5 wins none.
Which is cheaper?
Claude Sonnet 4.5 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 42 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 18 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.