Claude Opus 4.6 vs Claude Opus 5.5
Wins 0 of 8 areas
—
Wins 8 of 8 areas
Coding · Agents · Reasoning · Facts · Images and charts · Math · Long documents · Following instructions
Claude Opus 5.5 is the stronger all-rounder.
Scores updated · 32 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 software06Claude Opus 5.56 of 6 tests
- ReasoningHard problems that need careful thinking05Claude Opus 5.55 of 5 tests
- FactsGetting facts right instead of making them up03Claude Opus 5.53 of 3 tests
- MathCompetition and research-level math03Claude Opus 5.53 of 3 tests
- AgentsCarrying out multi-step tasks on its own01Claude Opus 5.51 of 1 test
- Images and chartsUnderstanding pictures, charts and video01Claude Opus 5.51 of 1 test
- Long documentsFinding answers in very long texts01Claude Opus 5.51 of 1 test
- Following instructionsDoing exactly what it is asked01Claude Opus 5.51 of 1 test
Agents, images and charts, 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.
Claude Opus 5.5 costs 20% 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 5.5 pulls ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+68.2points ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+36.5points ahead
- Short factual questions, answered correctlySimpleQA Verified+25.2points ahead
Where Claude Opus 4.6 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingClaude Opus 5.5
- SWE-bench ProClaude Opus 5.5 by 36.553.489.9+36.5
- LMArena · WebDevClaude Opus 5.5 by 269 rating points15461815+269 rating
- LiveBench · Agentic CodingClaude Opus 5.5 by 22.74971.7+22.7
- SWE-bench MultilingualClaude Opus 5.5 by 16.177.893.9+16.1
- SciCodeClaude Opus 5.5 by 1551.966.9+15
- LiveBench · CodingClaude Opus 5.5 by 11.178.289.3+11.1
ReasoningClaude Opus 5.5
- ARC-AGI-2Claude Opus 5.5 by 22.968.891.7+22.9
- Humanity's Last ExamClaude Opus 5.5 by 21.539.961.4+21.5
- SimpleBenchClaude Opus 5.5 by 20.867.688.4+20.8
- CritPtClaude Opus 5.5 by 19.112.631.7+19.1
- LiveBench · ReasoningClaude Opus 5.5 by 3.588.792.2+3.5
FactsClaude Opus 5.5
- SimpleQA VerifiedClaude Opus 5.5 by 25.24772.2+25.2
- AA-Omniscience · AccuracyClaude Opus 5.5 by 19.24766.2+19.2
- AA-Omniscience · Non-hallucinationClaude Opus 5.5 by 4.237.241.4+4.2
Images and chartsClaude Opus 5.5
- MMMU-ProClaude Opus 5.5 by 12.375.487.7+12.3
MathClaude Opus 5.5
- FrontierMath Tier 4Claude Opus 5.5 by 68.226.895+68.2
- FrontierMath Tiers 1-3 (v2)Claude Opus 5.5 by 25.26691.2+25.2
- LiveBench · MathematicsClaude Opus 5.5 by 7.889.397.1+7.8
Following instructionsClaude Opus 5.5
- LiveBench · Instruction FollowingClaude Opus 5.5 by 2.463.365.7+2.4
Other results11 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.
- SWE-bench MultimodalClaude Opus 5.5 by 34.327.161.4+34.3
- AA-OmniscienceClaude Opus 5.5 by 32.713.746.4+32.7
- AA IntelligenceClaude Opus 5.5 by 25.731.957.6+25.7
- LVBenchClaude Opus 5.5 by 20.76383.7+20.7
- GDPval-AA (Elo)Claude Opus 5.5 by 201 rating points16191820+201 rating
- OfficeQA ProClaude Opus 5.5 by 10.657.167.7+10.6
- livebench_data_analysisClaude Opus 5.5 by 10.469.980.3+10.4
- OfficeQAClaude Opus 5.5 by 5.473.578.9+5.4
- ARC-AGI-1Claude Opus 5.5 by 4.59397.5+4.5
- Legal Agent BenchmarkClaude Opus 5.5 by 4.14.28.3+4.1
- livebench_languageClaude Opus 5.5 by 383.386.3+3
Questions people ask
Which is better, Claude Opus 4.6 or Claude Opus 5.5?
Claude Opus 5.5 wins all eight areas we test: coding, agents, reasoning, facts, images and charts, math, long documents and following instructions. Claude Opus 4.6 wins none.
Which is better for coding?
Claude Opus 5.5. It wins 6 of the 6 coding tests both models report; Claude Opus 4.6 wins none.
Which is cheaper?
Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Opus 5.5 costs $4.00 and $20.00. That makes Claude Opus 5.5 about 20% cheaper for the same work.
How do you compare the two?
We use the 32 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 11 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.