Claude 3.7 Sonnet vs GPT-4.1
Wins 5 of 7 areas
Coding · Agents · Reasoning · Facts · Following instructions
Wins 2 of 7 areas
Images and charts · Long documents
Claude 3.7 Sonnet is the stronger all-rounder.GPT-4.1 is cheaper and better at images and charts.
Scores updated · 35 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 thinking30Claude 3.7 Sonnet3 of 4 tests · 1 tie
- CodingWriting and fixing software30Claude 3.7 Sonnet3 of 3 tests
- Following instructionsDoing exactly what it is asked20Claude 3.7 Sonnet2 of 2 tests
- FactsGetting facts right instead of making them up10Claude 3.7 Sonnet1 of 2 tests · 1 tie
- AgentsCarrying out multi-step tasks on its own10Claude 3.7 Sonnet1 of 1 test
- Images and chartsUnderstanding pictures, charts and video02GPT-4.12 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts01GPT-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 3.7 Sonnet pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+53.3points ahead
- Common-sense trick questionsSimpleBench+19.4points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+15.7points ahead
Every test, side by side
All 35 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude 3.7 Sonnet
- SWE-bench VerifiedClaude 3.7 Sonnet by 15.770.354.6+15.7
- Terminal-Bench HardClaude 3.7 Sonnet by 7.621.213.6+7.6
- SciCodeClaude 3.7 Sonnet by 2.240.338.1+2.2
ReasoningClaude 3.7 Sonnet
- SimpleBenchClaude 3.7 Sonnet by 19.446.427+19.4
- GPQA DiamondClaude 3.7 Sonnet by 10.677.266.6+10.6
- Humanity's Last ExamClaude 3.7 Sonnet by 5.59.74.2+5.5
- CritPttie0.90tie
FactsClaude 3.7 Sonnet
- AA-Omniscience · Non-hallucinationClaude 3.7 Sonnet by 53.3606.7+53.3
- AA-Omniscience · Accuracytie2827.8tie
Images and chartsGPT-4.1
- LMArena · VisionGPT-4.1 by 41 rating points11691210+41 rating
- MMMU-ProGPT-4.1 by 1.160.161.2+1.1
- MMMUtie7574.8tie
Following instructionsClaude 3.7 Sonnet
- Multi-ChallengeClaude 3.7 Sonnet by 13.351.638.3+13.3
- IFBenchClaude 3.7 Sonnet by 5.348.343+5.3
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 3.7 Sonnet by 38.9-0.7-39.6+38.9
- ARC-AGI-1Claude 3.7 Sonnet by 23.128.65.5+23.1
- AIR-Bench 2024Claude 3.7 Sonnet by 1781.864.8+17
- Artificial Analysis Coding IndexClaude 3.7 Sonnet by 14.636.421.8+14.6
- TAU-bench (retail)Claude 3.7 Sonnet by 13.281.268+13.2
- AA Agentic IndexClaude 3.7 Sonnet by 9.73727.3+9.7
- TAU-bench (airline)Claude 3.7 Sonnet by 958.449.4+9
- Aider-PolyglotClaude 3.7 Sonnet by 8.860.451.6+8.8
- AIME 2025Claude 3.7 Sonnet by 8.454.846.4+8.4
- τ²-Bench Telecom (AA run)Claude 3.7 Sonnet by 7.654.747.1+7.6
- HarmBenchGPT-4.1 by 7.484.391.7+7.4
- IFEvalClaude 3.7 Sonnet by 5.893.287.4+5.8
- AA IntelligenceClaude 3.7 Sonnet by 517.712.7+5
- Terminal-BenchClaude 3.7 Sonnet by 4.935.230.3+4.9
- XSTestGPT-4.1 by 1.596.497.9+1.5
- MMMLUGPT-4.1 by 1.286.187.3+1.2
- bbqtie92.192.6tie
- anthropic_red_teamtie99.799.3tie
- simple_safety_teststie100100tie
Questions people ask
Which is better, Claude 3.7 Sonnet or GPT-4.1?
Claude 3.7 Sonnet wins five of the seven areas where both have results: coding, agents, reasoning, facts and following instructions. GPT-4.1 wins images and charts and long documents, and costs 44% less.
Which is better for coding?
Claude 3.7 Sonnet. It wins 3 of the 3 coding tests both models report; GPT-4.1 wins none.
Which is cheaper?
Claude 3.7 Sonnet 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 35 benchmark tests both models have published scores on. The verdict counts the 16 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.