Claude Sonnet 4.6 vs GPT-5.1
Wins 4 of 7 areas
Coding · Agents · Reasoning · Facts
Wins 1 of 7 areas
Following instructions
Claude Sonnet 4.6 wins more areas, narrowly.GPT-5.1 is cheaper and better at following instructions.
Scores updated · 34 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 software50Claude Sonnet 4.65 of 5 tests
- AgentsCarrying out multi-step tasks on its own30Claude Sonnet 4.63 of 3 tests
- FactsGetting facts right instead of making them up31Claude Sonnet 4.63 of 4 tests
- ReasoningHard problems that need careful thinking21Claude Sonnet 4.62 of 4 tests · 1 tie
- Following instructionsDoing exactly what it is asked01GPT-5.11 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 each
- Long documentsFinding answers in very long texts00Even0 each · 1 tie
Long documents and following instructions 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-5.1 costs 38% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Claude Sonnet 4.6 pulls ahead
- Abstract visual puzzles that people can solveARC-AGI-2+40.7points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+23.9points ahead
- Real work tasks from 44 professionsGDPVal+20.2points ahead
Where GPT-5.1 pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+16.3points ahead
- Short factual questions, answered correctlySimpleQA Verified+15.2points ahead
- Harder college exam questions with imagesMMMU-Pro+2.2points ahead
Every test, side by side
All 34 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Sonnet 4.6
- Terminal-Bench 2.1Claude Sonnet 4.6 by 18.871.252.4+18.8
- LMArena · WebDevClaude Sonnet 4.6 by 126 rating points15211395+126 rating
- Terminal-Bench HardClaude Sonnet 4.6 by 7.55345.5+7.5
- SciCodeClaude Sonnet 4.6 by 6.850.143.3+6.8
- SWE-bench VerifiedClaude Sonnet 4.6 by 3.379.676.3+3.3
AgentsClaude Sonnet 4.6
- BrowseCompClaude Sonnet 4.6 by 23.974.750.8+23.9
- GDPValClaude Sonnet 4.6 by 20.236.716.5+20.2
- τ-Bench V3 · BankingClaude Sonnet 4.6 by 18.534.415.9+18.5
ReasoningClaude Sonnet 4.6
- ARC-AGI-2Claude Sonnet 4.6 by 40.758.317.6+40.7
- Humanity's Last ExamClaude Sonnet 4.6 by 5.133.628.5+5.1
- CritPtGPT-5.1 by 1.83.14.9+1.8
- GPQA Diamondtie87.587.3tie
FactsClaude Sonnet 4.6
- SimpleQA VerifiedGPT-5.1 by 15.232.848+15.2
- AA-Omniscience · Non-hallucinationClaude Sonnet 4.6 by 3.551.648.1+3.5
- AA-Omniscience · AccuracyClaude Sonnet 4.6 by 3.240.937.7+3.2
- Vectara HHEM hallucination ratelower is betterClaude Sonnet 4.6 by 1.510.612.1+1.5
Images and chartsEven
- LMArena · VisionClaude Sonnet 4.6 by 33 rating points12831250+33 rating
- MMMU-ProGPT-5.1 by 2.273.375.5+2.2
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.
- vectara_avg_summary_lengthGPT-5.1 by 139.7 rating points114.7254.4+139.7 rating
- τ²-Bench (Retail)Claude Sonnet 4.6 by 13.891.777.9+13.8
- Artificial Analysis Coding IndexClaude Sonnet 4.6 by 13.66349.4+13.6
- ARC-AGI-1Claude Sonnet 4.6 by 13.28672.8+13.2
- AA Agentic IndexClaude Sonnet 4.6 by 11.533.121.6+11.5
- Terminal-Bench 2.0Claude Sonnet 4.6 by 11.559.147.6+11.5
- AA-OmniscienceClaude Sonnet 4.6 by 6.812.25.4+6.8
- τ²-Bench Telecom (AA run)GPT-5.1 by 6.275.781.9+6.2
- AA IntelligenceClaude Sonnet 4.6 by 5.430.124.7+5.4
- frontiermath_tier_4_v1GPT-5.1 by 4.28.312.5+4.2
- HLE (with tools)Claude Sonnet 4.6 by 4.146.842.7+4.1
- MMMLUGPT-5.1 by 1.789.391+1.7
- vectara_factual_consistencyClaude Sonnet 4.6 by 1.589.487.9+1.5
- vectara_answer_ratetie99.9100tie
Questions people ask
Which is better, Claude Sonnet 4.6 or GPT-5.1?
Claude Sonnet 4.6 wins four of the seven areas where both have results: coding, agents, reasoning and facts. GPT-5.1 wins following instructions, and costs 38% less. They are level on images and charts and long documents.
Which is better for coding?
Claude Sonnet 4.6. It wins 5 of the 5 coding tests both models report; GPT-5.1 wins none.
Which is cheaper?
Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; GPT-5.1 costs $1.25 and $10.00. That makes GPT-5.1 about 38% cheaper for the same work.
How do you compare the two?
We use the 34 benchmark tests both models have published scores on. The verdict counts the 20 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.