Claude Opus 4.1 vs Claude Opus 4.6
Wins 1 of 8 areas
Following instructions
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents
Claude Opus 4.6 is the stronger all-rounder.Claude Opus 4.1 is better at following instructions.
Scores updated · 29 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 software04Claude Opus 4.64 of 4 tests
- ReasoningHard problems that need careful thinking03Claude Opus 4.63 of 3 tests
- AgentsCarrying out multi-step tasks on its own02Claude Opus 4.62 of 2 tests
- MathCompetition and research-level math02Claude Opus 4.62 of 2 tests
- FactsGetting facts right instead of making them up01Claude Opus 4.61 of 2 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video01Claude Opus 4.61 of 1 test
- Long documentsFinding answers in very long texts01Claude Opus 4.61 of 1 test
- Following instructionsDoing exactly what it is asked20Claude Opus 4.12 of 2 tests
Images and charts 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.
Claude Opus 4.6 costs 67% 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 Opus 4.6 pulls ahead
- Unpublished advanced math problemsFrontierMath Tiers 1-3 (v2)+53.4points ahead
- Completes tasks by operating a computer desktopOSWorld-Verified+28.3points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+27.4points ahead
Where Claude Opus 4.1 pulls ahead
- Keeps track of context across a multi-turn chatMulti-Challenge+20points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.3points ahead
Every test, side by side
All 29 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 4.6
- LMArena · WebDevClaude Opus 4.6 by 156 rating points13901546+156 rating
- Terminal-Bench HardClaude Opus 4.6 by 11.934.346.2+11.9
- SciCodeClaude Opus 4.6 by 1140.951.9+11
- SWE-bench VerifiedClaude Opus 4.6 by 6.374.580.8+6.3
AgentsClaude Opus 4.6
- OSWorld-VerifiedClaude Opus 4.6 by 28.344.472.7+28.3
- MCP AtlasClaude Opus 4.6 by 21.840.962.7+21.8
ReasoningClaude Opus 4.6
- Humanity's Last ExamClaude Opus 4.6 by 27.412.539.9+27.4
- CritPtClaude Opus 4.6 by 12.6012.6+12.6
- GPQA DiamondClaude Opus 4.6 by 8.780.989.6+8.7
FactsClaude Opus 4.6
- SimpleQA VerifiedClaude Opus 4.6 by 12.234.847+12.2
- Vectara HHEM hallucination ratelower is bettertie11.812.2tie
Images and chartsClaude Opus 4.6
- MMMU-ProClaude Opus 4.6 by 7.567.975.4+7.5
MathClaude Opus 4.6
- FrontierMath Tiers 1-3 (v2)Claude Opus 4.6 by 53.412.666+53.4
- FrontierMath Tier 4Claude Opus 4.6 by 24.42.426.8+24.4
Following instructionsClaude Opus 4.1
- Multi-ChallengeClaude Opus 4.1 by 2057.237.1+20
- IFBenchClaude Opus 4.1 by 2.355.453.1+2.3
Other results12 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.
- AIME 2025Claude Opus 4.6 by 21.87899.8+21.8
- τ²-Bench Telecom (AA run)Claude Opus 4.6 by 20.771.492.1+20.7
- Terminal-Bench 2.0Claude Opus 4.6 by 18.946.565.4+18.9
- frontiermath_tier_4_v1Claude Opus 4.6 by 18.74.222.9+18.7
- Artificial Analysis Coding IndexClaude Opus 4.6 by 11.636.548.1+11.6
- AA IntelligenceClaude Opus 4.6 by 9.122.831.9+9.1
- vectara_answer_rateClaude Opus 4.6 by 7.492.499.8+7.4
- τ²-Bench (Retail)Claude Opus 4.6 by 5.186.891.9+5.1
- MMMLUClaude Opus 4.6 by 1.689.591.1+1.6
- metr_swaaClaude Opus 4.1 by 1.510098.5+1.5
- vectara_avg_summary_lengthtie129.1137.6tie
- vectara_factual_consistencytie88.287.8tie
Questions people ask
Which is better, Claude Opus 4.1 or Claude Opus 4.6?
Claude Opus 4.6 wins seven of the eight areas we test: coding, agents, reasoning, facts, images and charts, math and long documents. Claude Opus 4.1 wins following instructions.
Which is better for coding?
Claude Opus 4.6. It wins 4 of the 4 coding tests both models report; Claude Opus 4.1 wins none.
Which is cheaper?
Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; Claude Opus 4.6 costs $5.00 and $25.00. That makes Claude Opus 4.6 about 67% cheaper for the same work.
How do you compare the two?
We use the 29 benchmark tests both models have published scores on. The verdict counts the 17 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 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.