Claude Sonnet 4 vs GPT-4.1 mini
Wins 7 of 7 areas
Coding · Agents · Reasoning · Facts · Images and charts · Long documents · Following instructions
Wins 0 of 7 areas
—
Claude Sonnet 4 is the stronger all-rounder.GPT-4.1 mini is cheaper.
Scores updated · 37 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 software30Claude Sonnet 43 of 4 tests · 1 tie
- ReasoningHard problems that need careful thinking30Claude Sonnet 43 of 4 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video30Claude Sonnet 43 of 3 tests
- AgentsCarrying out multi-step tasks on its own20Claude Sonnet 42 of 2 tests
- FactsGetting facts right instead of making them up20Claude Sonnet 42 of 2 tests
- Following instructionsDoing exactly what it is asked20Claude Sonnet 42 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 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 mini costs 89% 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 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+63.6points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+49.1points ahead
- Reasons across sets of long documentsAA-LCR+26.3points ahead
Where GPT-4.1 mini pulls ahead
No clear win on a test scored out of 100.
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.
CodingClaude Sonnet 4
- SWE-bench VerifiedClaude Sonnet 4 by 49.172.723.6+49.1
- Terminal-Bench 2.1Claude Sonnet 4 by 26.236.310.1+26.2
- Terminal-Bench HardClaude Sonnet 4 by 23.531.17.6+23.5
- SciCodetie4040.4tie
AgentsClaude Sonnet 4
- τ-Bench V3 · BankingClaude Sonnet 4 by 11.316.75.4+11.3
- GDPValClaude Sonnet 4 by 9.79.70+9.7
ReasoningClaude Sonnet 4
- GPQA DiamondClaude Sonnet 4 by 11.377.766.4+11.3
- ARC-AGI-2Claude Sonnet 4 by 5.95.90+5.9
- Humanity's Last ExamClaude Sonnet 4 by 5.710.75+5.7
- CritPttie0.30tie
FactsClaude Sonnet 4
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 63.670.97.3+63.6
- AA-Omniscience · AccuracyClaude Sonnet 4 by 2.422.720.3+2.4
Images and chartsClaude Sonnet 4
- MMMU-ProClaude Sonnet 4 by 3.161.858.7+3.1
- MMMUClaude Sonnet 4 by 1.774.472.7+1.7
- LMArena · VisionClaude Sonnet 4 by 10 rating points11911181+10 rating
Following instructionsClaude Sonnet 4
- Multi-ChallengeClaude Sonnet 4 by 21.357.135.8+21.3
- IFBenchClaude Sonnet 4 by 16.454.738.3+16.4
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.
- AA-OmniscienceClaude Sonnet 4 by 53.80.2-53.6+53.8
- ARC-AGI-1Claude Sonnet 4 by 36.5403.5+36.5
- Aider-PolyglotClaude Sonnet 4 by 3670.734.7+36
- AIME 2025Claude Sonnet 4 by 30.370.540.2+30.3
- AIR-Bench 2024Claude Sonnet 4 by 27.988.360.4+27.9
- TAU-bench (retail)Claude Sonnet 4 by 24.780.555.8+24.7
- TAU-bench (airline)Claude Sonnet 4 by 246036+24
- HMMT 2025GPT-4.1 mini by 19.115.935+19.1
- Artificial Analysis Coding IndexClaude Sonnet 4 by 17.437.620.2+17.4
- AA Agentic IndexClaude Sonnet 4 by 15.817.61.8+15.8
- HarmBenchClaude Sonnet 4 by 12.49885.6+12.4
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 11.764.652.9+11.7
- AA IntelligenceClaude Sonnet 4 by 8.718.910.2+8.7
- MMMLUClaude Sonnet 4 by 886.578.5+8
- bbqClaude Sonnet 4 by 4.596.692.1+4.5
- IFEvalClaude Sonnet 4 by 3.587.684.1+3.5
- XSTesttie96.697.4tie
- anthropic_red_teamtie99.299.3tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude Sonnet 4 or GPT-4.1 mini?
Claude Sonnet 4 wins all seven areas where both have results: coding, agents, reasoning, facts, images and charts, long documents and following instructions. GPT-4.1 mini wins none, but costs 89% less.
Which is better for coding?
Claude Sonnet 4. It wins 3 of the 4 coding tests both models report; GPT-4.1 mini wins none, and 1 is a tie.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-4.1 mini costs $0.40 and $1.60. That makes GPT-4.1 mini about 89% 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 18 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.