Claude 3.7 Sonnet vs Claude Sonnet 4.5
Wins 1 of 7 areas
Agents
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
Claude Sonnet 4.5 is the stronger all-rounder.Claude 3.7 Sonnet is better at agents.
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.
- ReasoningHard problems that need careful thinking03Claude Sonnet 4.53 of 4 tests · 1 tie
- CodingWriting and fixing software03Claude Sonnet 4.53 of 3 tests
- Images and chartsUnderstanding pictures, charts and video02Claude Sonnet 4.52 of 2 tests
- Following instructionsDoing exactly what it is asked02Claude Sonnet 4.52 of 2 tests
- Long documentsFinding answers in very long texts01Claude Sonnet 4.51 of 1 test
- AgentsCarrying out multi-step tasks on its own10Claude 3.7 Sonnet1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents and long documents 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 4.5 pulls ahead
- Reasons across sets of long documentsAA-LCR+20.6points ahead
- Hard command-line tasks in a real terminalTerminal-Bench Hard+14.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+9points ahead
Where Claude 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+9.1points ahead
- Real work tasks from 44 professionsGDPVal+6.9points 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 4.5
- Terminal-Bench HardClaude Sonnet 4.5 by 14.421.235.6+14.4
- SWE-bench VerifiedClaude Sonnet 4.5 by 6.970.377.2+6.9
- SciCodeClaude Sonnet 4.5 by 5.440.345.7+5.4
ReasoningClaude Sonnet 4.5
- Humanity's Last ExamClaude Sonnet 4.5 by 8.19.717.8+8.1
- SimpleBenchClaude Sonnet 4.5 by 7.946.454.3+7.9
- GPQA DiamondClaude Sonnet 4.5 by 6.277.283.4+6.2
- CritPttie0.91.1tie
FactsEven
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 9.16050.9+9.1
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 4.92832.9+4.9
Images and chartsClaude Sonnet 4.5
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 20.651.772.3+20.6
Following instructionsClaude Sonnet 4.5
- IFBenchClaude Sonnet 4.5 by 948.357.3+9
- Multi-ChallengeClaude Sonnet 4.5 by 3.751.655.3+3.7
Other results19 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.
- HMMT Feb. 2025Claude Sonnet 4.5 by 35.831.767.5+35.8
- ARC-AGI-1Claude Sonnet 4.5 by 35.128.663.7+35.1
- AIME 2025Claude Sonnet 4.5 by 32.254.887+32.2
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 23.454.778.1+23.4
- AA Agentic IndexClaude 3.7 Sonnet by 19.53717.5+19.5
- swe_bench_bashClaude Sonnet 4.5 by 18.652.871.4+18.6
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 15.736.452.1+15.7
- Terminal-BenchClaude Sonnet 4.5 by 14.835.250+14.8
- TAU-bench (airline)Claude Sonnet 4.5 by 11.658.470+11.6
- AIR-Bench 2024Claude Sonnet 4.5 by 881.889.8+8
- HarmBenchClaude Sonnet 4.5 by 7.784.392+7.7
- bbqClaude Sonnet 4.5 by 6.892.198.9+6.8
- TAU-bench (retail)Claude Sonnet 4.5 by 581.286.2+5
- AA IntelligenceClaude Sonnet 4.5 by 317.720.7+3
- MMMLUClaude Sonnet 4.5 by 386.189.1+3
- anthropic_red_teamClaude 3.7 Sonnet by 1.599.798.2+1.5
- AA-Omnisciencetie-0.7-0.1tie
- simple_safety_teststie100100tie
- XSTesttie96.496.4tie
Questions people ask
Which is better, Claude 3.7 Sonnet or Claude Sonnet 4.5?
Claude Sonnet 4.5 wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. Claude 3.7 Sonnet wins agents. They are level on facts.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; Claude 3.7 Sonnet wins none.
Which is cheaper?
Claude 3.7 Sonnet costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Sonnet 4.5 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 15 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 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.