Claude Sonnet 4 vs GPT-4.1
Wins 4 of 7 areas
Coding · Reasoning · Long documents · Following instructions
Wins 3 of 7 areas
Agents · Facts · Images and charts
Claude Sonnet 4 wins more areas, narrowly.GPT-4.1 is cheaper and better at facts.
Scores updated · 44 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 software40Claude Sonnet 44 of 4 tests
- ReasoningHard problems that need careful thinking30Claude Sonnet 43 of 4 tests · 1 tie
- Following instructionsDoing exactly what it is asked20Claude Sonnet 42 of 2 tests
- Long documentsFinding answers in very long texts10Claude Sonnet 41 of 1 test
- FactsGetting facts right instead of making them up12GPT-4.12 of 3 tests
- Images and chartsUnderstanding pictures, charts and video01GPT-4.11 of 3 tests · 2 ties
- AgentsCarrying out multi-step tasks on its own01GPT-4.11 of 1 test
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.
GPT-4.1 costs 44% 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+64.2points ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+18.8points ahead
- Common-sense trick questionsSimpleBench+18.5points ahead
Where GPT-4.1 pulls ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+5.1points ahead
- Real work tasks from 44 professionsGDPVal+4.1points ahead
Every test, side by side
All 44 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 18.172.754.6+18.1
- Terminal-Bench HardClaude Sonnet 4 by 17.531.113.6+17.5
- LiveCodeBench v6Claude Sonnet 4 by 3.848.544.7+3.8
- SciCodeClaude Sonnet 4 by 1.94038.1+1.9
ReasoningClaude Sonnet 4
- SimpleBenchClaude Sonnet 4 by 18.545.527+18.5
- GPQA DiamondClaude Sonnet 4 by 11.177.766.6+11.1
- Humanity's Last ExamClaude Sonnet 4 by 6.510.74.2+6.5
- CritPttie0.30tie
FactsGPT-4.1
- AA-Omniscience · Non-hallucinationClaude Sonnet 4 by 64.270.96.7+64.2
- AA-Omniscience · AccuracyGPT-4.1 by 5.122.727.8+5.1
- Vectara HHEM hallucination ratelower is betterGPT-4.1 by 4.710.35.6+4.7
Images and chartsGPT-4.1
- LMArena · VisionGPT-4.1 by 19 rating points11911210+19 rating
- MMMU-Protie61.861.2tie
- MMMUtie74.474.8tie
Following instructionsClaude Sonnet 4
- Multi-ChallengeClaude Sonnet 4 by 18.857.138.3+18.8
- IFBenchClaude Sonnet 4 by 11.754.743+11.7
Other results26 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 39.80.2-39.6+39.8
- ARC-AGI-1Claude Sonnet 4 by 34.5405.5+34.5
- AIME 2025Claude Sonnet 4 by 24.170.546.4+24.1
- AIR-Bench 2024Claude Sonnet 4 by 23.588.364.8+23.5
- Aider-PolyglotClaude Sonnet 4 by 19.170.751.6+19.1
- τ²-Bench Telecom (AA run)Claude Sonnet 4 by 17.564.647.1+17.5
- Artificial Analysis Coding IndexClaude Sonnet 4 by 15.837.621.8+15.8
- HMMT 2025GPT-4.1 by 1315.928.9+13
- TAU-bench (retail)Claude Sonnet 4 by 12.580.568+12.5
- TAU-bench (airline)Claude Sonnet 4 by 10.66049.4+10.6
- AA Agentic IndexGPT-4.1 by 9.717.627.3+9.7
- HarmBenchClaude Sonnet 4 by 6.39891.7+6.3
- AA IntelligenceClaude Sonnet 4 by 6.218.912.7+6.2
- vectara_avg_summary_lengthClaude Sonnet 4 by 54.1 rating points145.891.7+54.1 rating
- Terminal-BenchClaude Sonnet 4 by 5.235.530.3+5.2
- vectara_factual_consistencyGPT-4.1 by 4.789.794.4+4.7
- OJBenchGPT-4.1 by 4.215.319.5+4.2
- bbqClaude Sonnet 4 by 496.692.6+4
- MultiPL-EClaude Sonnet 4 by 1.988.686.7+1.9
- vectara_answer_rateGPT-4.1 by 1.398.699.9+1.3
- XSTestGPT-4.1 by 1.396.697.9+1.3
- MMMLUtie86.587.3tie
- IFEvaltie87.687.4tie
- anthropic_red_teamtie99.299.3tie
- frontiermath_tier_4_v1tie00tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude Sonnet 4 or GPT-4.1?
Claude Sonnet 4 wins four of the seven areas where both have results: coding, reasoning, long documents and following instructions. GPT-4.1 wins agents, facts and images and charts, and costs 44% less.
Which is better for coding?
Claude Sonnet 4. It wins 4 of the 4 coding tests both models report; GPT-4.1 wins none.
Which is cheaper?
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-4.1 costs $2.00 and $8.00. That makes GPT-4.1 about 44% cheaper for the same work.
How do you compare the two?
We use the 44 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 26 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.