Claude Sonnet 4.5 vs GPT-4.1 nano
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.GPT-4.1 nano is cheaper.
Scores updated · 33 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 thinking40Claude Sonnet 4.54 of 4 tests
- Images and chartsUnderstanding pictures, charts and video40Claude Sonnet 4.54 of 4 tests
- CodingWriting and fixing software30Claude Sonnet 4.53 of 3 tests
- FactsGetting facts right instead of making them up30Claude Sonnet 4.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 4.52 of 2 tests
- Following instructionsDoing exactly what it is asked20Claude Sonnet 4.52 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
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.
GPT-4.1 nano costs 97% 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 Claude Sonnet 4.5 pulls ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+52.1points ahead
- Reasons across sets of long documentsAA-LCR+52points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+40.3points ahead
Where GPT-4.1 nano pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- Terminal-Bench 2.1Claude Sonnet 4.5 by 52.155.83.7+52.1
- Terminal-Bench HardClaude Sonnet 4.5 by 31.835.63.8+31.8
- SciCodeClaude Sonnet 4.5 by 19.845.725.9+19.8
AgentsClaude Sonnet 4.5
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 2124.53.5+21
- GDPValClaude Sonnet 4.5 by 20.520.50+20.5
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 32.283.451.2+32.2
- Humanity's Last ExamClaude Sonnet 4.5 by 1417.83.8+14
- ARC-AGI-2Claude Sonnet 4.5 by 13.613.60+13.6
- CritPtClaude Sonnet 4.5 by 1.11.10+1.1
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 33.550.917.4+33.5
- SimpleQA VerifiedClaude Sonnet 4.5 by 24.730.76+24.7
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 19.232.913.7+19.2
Images and chartsClaude Sonnet 4.5
- MMMU-ProClaude Sonnet 4.5 by 28.668.740.1+28.6
- CharXiv (RQ)Claude Sonnet 4.5 by 26.767.240.5+26.7
- MMMUClaude Sonnet 4.5 by 24.279.655.4+24.2
- MathVistaClaude Sonnet 4.5 by 23.679.856.2+23.6
Following instructionsClaude Sonnet 4.5
- Multi-ChallengeClaude Sonnet 4.5 by 40.355.315+40.3
- IFBenchClaude Sonnet 4.5 by 25.357.332+25.3
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 4.5 by 63.763.70+63.7
- TAU-bench (retail)Claude Sonnet 4.5 by 63.686.222.6+63.6
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 60.878.117.3+60.8
- AA-OmniscienceClaude Sonnet 4.5 by 57.5-0.1-57.6+57.5
- TAU-bench (airline)Claude Sonnet 4.5 by 567014+56
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 4152.111.1+41
- AIR-Bench 2024Claude Sonnet 4.5 by 28.389.861.5+28.3
- MMMLUClaude Sonnet 4.5 by 22.289.166.9+22.2
- AA IntelligenceClaude Sonnet 4.5 by 12.920.77.8+12.9
- bbqClaude Sonnet 4.5 by 11.498.987.5+11.4
- HarmBenchClaude Sonnet 4.5 by 5.29286.8+5.2
- anthropic_red_teamGPT-4.1 nano by 1.498.299.6+1.4
- simple_safety_testsClaude Sonnet 4.5 by 110099+1
- XSTesttie96.496tie
Questions people ask
Which is better, Claude Sonnet 4.5 or GPT-4.1 nano?
Claude Sonnet 4.5 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. GPT-4.1 nano wins none, but costs 97% less.
Which is better for coding?
Claude Sonnet 4.5. It wins 3 of the 3 coding tests both models report; GPT-4.1 nano wins none.
Which is cheaper?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-4.1 nano costs $0.10 and $0.40. That makes GPT-4.1 nano about 97% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 19 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.