Claude Sonnet 4.5 vs GPT-4.1 mini
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Wins 0 of 8 areas
—
Claude Sonnet 4.5 is the stronger all-rounder.GPT-4.1 mini is cheaper.
Scores updated · 39 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. 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 4.54 of 4 tests
- 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
- 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
- MathCompetition and research-level math10Claude Sonnet 4.51 of 1 test
- Long documentsFinding answers in very long texts10Claude Sonnet 4.51 of 1 test
Math 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 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 4.5 pulls ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+53.6points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+45.7points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+43.6points ahead
Where GPT-4.1 mini pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 39 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.5
- SWE-bench VerifiedClaude Sonnet 4.5 by 53.677.223.6+53.6
- Terminal-Bench 2.1Claude Sonnet 4.5 by 45.755.810.1+45.7
- Terminal-Bench HardClaude Sonnet 4.5 by 2835.67.6+28
- SciCodeClaude Sonnet 4.5 by 5.345.740.4+5.3
AgentsClaude Sonnet 4.5
- GDPValClaude Sonnet 4.5 by 20.520.50+20.5
- τ-Bench V3 · BankingClaude Sonnet 4.5 by 19.124.55.4+19.1
ReasoningClaude Sonnet 4.5
- GPQA DiamondClaude Sonnet 4.5 by 1783.466.4+17
- ARC-AGI-2Claude Sonnet 4.5 by 13.613.60+13.6
- Humanity's Last ExamClaude Sonnet 4.5 by 12.817.85+12.8
- CritPtClaude Sonnet 4.5 by 1.11.10+1.1
FactsClaude Sonnet 4.5
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.5 by 43.650.97.3+43.6
- SimpleQA VerifiedClaude Sonnet 4.5 by 1830.712.7+18
- AA-Omniscience · AccuracyClaude Sonnet 4.5 by 12.632.920.3+12.6
Images and chartsClaude Sonnet 4.5
- CharXiv (RQ)Claude Sonnet 4.5 by 10.467.256.8+10.4
- MMMU-ProClaude Sonnet 4.5 by 1068.758.7+10
- MMMUClaude Sonnet 4.5 by 6.979.672.7+6.9
- MathVistaClaude Sonnet 4.5 by 6.779.873.1+6.7
MathClaude Sonnet 4.5
- FrontierMath Tiers 1-3 (v2)Claude Sonnet 4.5 by 17.223.96.7+17.2
Long documentsClaude Sonnet 4.5
- AA-LCRClaude Sonnet 4.5 by 28.372.344+28.3
Following instructionsClaude Sonnet 4.5
- Multi-ChallengeClaude Sonnet 4.5 by 19.555.335.8+19.5
- IFBenchClaude Sonnet 4.5 by 1957.338.3+19
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 4.5 by 60.263.73.5+60.2
- AA-OmniscienceClaude Sonnet 4.5 by 53.5-0.1-53.6+53.5
- swe_bench_bashClaude Sonnet 4.5 by 47.571.423.9+47.5
- AIME 2025Claude Sonnet 4.5 by 46.88740.2+46.8
- HMMT 2025Claude Sonnet 4.5 by 39.674.635+39.6
- TAU-bench (airline)Claude Sonnet 4.5 by 347036+34
- Artificial Analysis Coding IndexClaude Sonnet 4.5 by 31.952.120.2+31.9
- TAU-bench (retail)Claude Sonnet 4.5 by 30.486.255.8+30.4
- AIR-Bench 2024Claude Sonnet 4.5 by 29.489.860.4+29.4
- τ²-Bench Telecom (AA run)Claude Sonnet 4.5 by 25.278.152.9+25.2
- AA Agentic IndexClaude Sonnet 4.5 by 15.717.51.8+15.7
- MMMLUClaude Sonnet 4.5 by 10.689.178.5+10.6
- AA IntelligenceClaude Sonnet 4.5 by 10.520.710.2+10.5
- bbqClaude Sonnet 4.5 by 6.898.992.1+6.8
- HarmBenchClaude Sonnet 4.5 by 6.49285.6+6.4
- anthropic_red_teamGPT-4.1 mini by 1.198.299.3+1.1
- XSTestGPT-4.1 mini by 196.497.4+1
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude Sonnet 4.5 or GPT-4.1 mini?
Claude Sonnet 4.5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. GPT-4.1 mini wins none, but costs 89% less.
Which is better for coding?
Claude Sonnet 4.5. It wins 4 of the 4 coding tests both models report; GPT-4.1 mini 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 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 39 benchmark tests both models have published scores on. The verdict counts the 21 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.