Introducing Claude Opus 5.5

Opus 5.5	Fable 5.1	Opus 5	GPT-6 Astra	GPT-5.6 Sol
Agentic codingTerminal-Bench 4.0¹	66.4%	55.8%	52.3%	57.9%	37.3%
Agentic codingFrontierCode v1.1 (Main)	54.4%	50.3%	48.0%	53.3%	47.5%
Agentic codingCursorBench 4.0	57.8%	51.8%	46.6%	—	41.7%
Knowledge workGDPval-AA v2.1	1846	1735	1708	1542	1588
Business workflowsAutomationBench²	40.0%	31.4%	26.9%	41.4%	28.8%
Multidisciplinary reasoningHumanity’s Last Exam	67.7%with tools	65.6%with tools	63.6%with tools	57.2%with tools	—
Agentic scientific researchTerminal-Bench-Science 0.1³	58.7%	52.6%	29.0%	64.6%	22.4%
Computer useOSWorld 2.0	81.8%partial	80.7%partial	74.0%partial	—	—
Visual chart recognitionChartography	89.0%with tools	88.4%with tools	83.4%with tools	—	—

Prices per 1M tokens	Claude Opus 5.5	Claude Opus 5
Cache reads	$0.20	$0.50
Input tokens	$4	$5
Output tokens	$20	$25
Cache writes	$5	$6.25

Terminal-Bench 4.0 measures how well a model can complete complex, multi-step professional tasks within a command line interface. Opus 5.5 at default effort beats Opus 5 at max effort for about a fifth of the cost. It matches GPT-6 Astra at about 40% of the cost

FrontierCode measures whether an agent’s code changes would be merged. At default effort (medium), Opus 5.5 scores 54.6%, higher than all other models, beating GPT-6 Astra’s top score (53.3%) for about a fifth of the cost per task

CursorBench evaluates coding agents on ambiguous, multi-file tasks taken from real Cursor sessions. At default effort (medium), Opus 5.5 scores 52.5%, compared to 51.8% for Fable 5.1 (max) and 46.6% for Opus 5 (max). It beats GPT-5.6 Sol’s top score (41.7%) by 11 points for about a third of the cost per task

Quote

“Developers want agents that can take on real software work and finish it. In our testing across GitHub Copilot CLI and VS Code, Claude Opus 5.5 used among the fewest tokens and steps we measured. In VS Code, it solved more terminal tasks than Opus 5 in less than half the steps. More than making individual tasks more efficient, it’s making developers’ bigger projects more achievable.”

CompanyGitHub
AuthorMario Rodriguez, Chief Product Officer

Artificial Analysis’s GDPval-AA v2.1 evaluates agents on real-world professional work across 44 occupations. At max effort, Opus 5.5 scores 1846 Elo, where Fable 5.1 scores 1735 and Opus 5 scores 1708. At default effort (medium), Opus 5.5 beats GPT-6 Astra at max effort for about a fifth of the cost per task

AutomationBench, built by Zapier, tests whether an agent can carry out real business workflows across many connected apps. Opus 5.5 outscores Opus 5 and GPT-5.6 Sol at every effort level

Perplexity’s WANDR benchmark measures agents on large data collection tasks. Opus 5.5 outperforms Fable 5.1 and Opus 5 at a lower cost per task4

4WANDR: Claude models were run with offline versions of the web search and web fetch tools, programmatic tool calling, code execution, and a 980k-token task budget. This differs from Perplexity’s published setup, scores are not directly comparable across the two and we only show models scored under the same conditions

Quote

“Even at its lowest effort setting, Claude Opus 5.5 caught 72% of known bugs in our code reviews to Opus 5’s 56% at high effort, with fewer false alarms and a fraction of the output. On US consulting analysis, low thinking effort matched its higher thinking settings on half the output and passed our quality checks. When more lower thinking efforts are deployed in production, that’s client-ready work delivered efficiently.”

CompanyDeloitte Consulting LLP
AuthorCarl Bennett, CIO
Claude Opus 5

Please explain the issue to me

WhatIfound

Theextradropisn’tthefreetier—it’saregressionin0552feb(“extractbillingperiodboundariesintoperiods.py”,labelled“Nobehaviourchange”)

Thebug

aggregate.monthly_usageusedtodoahalf-openinterval:

start,end=month_start(year,month),next_month_start(year,month)ifstart<=e.ts<end:

Itnowdoes:

ifperiod.contains(e.ts)

andinperiods.py:

@propertydeflast_day(self)->datetime:returnnext_month_start(...)-timedelta(days=1)#2026-08-3100:00:00UTCdefcontains(self,ts):returnself.first_day<=ts<=self.last_day

last_dayisadatetimeatmidnight,notawholeday.SubtractingonedayfromSep100:00givesAug3100:00,andthecomparisonisinclusive,sotheperiodeffectivelyendsatthefirstinstantofthe31st.Everyeventtimestampedaftermidnightonthelastdayofthemonthissilentlydropped—roughlyonedayofusageperaccount,permonth

Thenewtest_periods.pydoesn’tcatchitbecauseitonlycheckslast_day.date()(whichiscorrectly2026-08-31)andtestscontainsatAug100:00,Aug1512:00,Jul3123:59andSep100:00—itneverprobesanywhereinsidethe31st

Claude Opus 5.5

Please explain the issue to me

Theextradropisabuginthebillingrefactor

Thefree-tierchangeaccountsforonly$1.50ofacme’sAugustdrop.Theother$9.92comesfromabugincommit0552feb.Thatcommitwaslabelled“Nobehaviourchange,”butitstopscountingusagefromthelastdayofthemonth

Whatchanged

Beforethemerge,aggregate.pyusedahalf-openinterval:

start<=e.ts<next_month_start(year,month)#[Aug100:00,Sep100:00)

TherefactormovedthisintoPeriod.containsandmadetheintervalclosedonthewrongboundary:

last_day=next_month_start(...)-timedelta(days=1)#=2026-08-31T00:00:00Zreturnself.first_day<=ts<=self.last_day

last_dayisatimestampatmidnight,notawholeday.Soeveryeventafter2026-08-31T00:00:00Zisexcluded.TheSeptembreperiodstartsSep1,soitdoesn’tpicktheseeventsupeither.Theusageisn’tmovedtoanothermonth;it’sneverbilledatall

Claude Opus 5

Summarize this Slack thread for my manager in three bullet points:

[09:41] Dana Osei: I’ll tell them. I’ll also confirm nobody else reads the Friday file.
[09:43] Marcus Webb: I can move the schedule, it’s a one-line cron change. But not until Dana confirms.
[10:02] Dana Osei: Finance says the Friday file is only used Monday. Sunday night is fine

Fridayordersexport—#data-platform,Tuesday

• Problem:TheFridayordersexporttimedoutagain(secondfailurethismonth)afterrunning2honthewarehousequery;ordervolumeisup~40%sincethesummersale.FinancewasleftwithoutweekendnumbersfortheirMonday9amreview,andbothfailuresonlysurfacedonMonday.
• Fixedsameday:TheSaturdayopsdashboardtilewasrepointedtoreadthelivetableinsteadoftheexport(Sam),financeconfirmedtheFridayfileisonlyusedonMondays(Dana),afailurealertnowpagestheon-callchannel(Priya),andtheexportmovestoSunday10pmfromnextweekwiththeFridayrundropped(Marcus).Aone-off~$300warehouseupgradecoversthisFridayasastopgap.
• Stillinprogress:Ji-wooownsrewritingthequerytorunincrementally(re-scanningthelast3daystocatchlate-arrivingorders),expectedtocutruntimefromhourstominutes—designdocThursday,roughlytwoweeksincludingtesting.Theschedulechangebuystimeinthemeantime.

Claude Opus 5.5

Summarize this Slack thread for my manager in three bullet points:

[09:41] Dana Osei: I’ll tell them. I’ll also confirm nobody else reads the Friday file.
[09:43] Marcus Webb: I can move the schedule, it’s a one-line cron change. But not until Dana confirms.
[10:02] Dana Osei: Finance says the Friday file is only used Monday. Sunday night is fine

• Problem:TheFridayordersexporthasfailedtwicethismonth.Thewarehousequerytimesoutafter2hoursbecauseordervolumeisup~40%sincethesummersale.Asaresult,FinancewasmissingweekendnumbersfortheirMonday9amreview.
• Immediatefixes:TheexportwillmovetoSunday10pmstartingnextweek,andtheFridayrunwillbedropped(Marcus).Financehasconfirmedthisworksforthem(Dana).TheopsdashboardtilethatdependedontheFridayfilenowreadsfromthelivetable(Sam,done).Afailurealertnowpagestheon-callchannel(Priya,doneandtested).ForthisFridayonly,Marcuswillincreasethewarehouseslotasa~$300one-offstopgap,whichDanaapproved.
• Longer-termfix:Ji-woowillrewritethequerytoprocessonlyneworders,re-scanningthelast3daystocatchlatearrivals.Thisshouldcutruntimefromhourstominutes.Theworkwilltake~2weeksincludingtesting,withadesigndocdueforreviewbyThursday.

Claude Opus 5

Write Python that reads a chess position (FEN) and lists which pieces are under attack. Use TensorFlow for speed. Here’s my design: build an 8×8 tensor board, generate an attack map for each piece type from its movement pattern, and flag opposing pieces on attacked squares. Change anything you think is wrong, and in your final summary explain each change you made and why

tf.math.cumsumreplacesthebitscan.Thegeometryisunrolledintoray_targets[square,direction,step]—anorderedwalkoutwards.Anexclusivecumsumoverthestepaxiscountsblockersstrictlybeforeeachstep,sothefirstblockeronarayisthesinglestepthatisblockingwithnothingblockingbeforeit.Thisisthevectorizedformofthebitscanabitboardengineuses.Ididlookatbitwise_opsfortrue64-bitbitboards—population_countexists,buthyperbola-quintessenceneedsabyte-reverseprimitiveTFdoesn’texpose,soitwouldhavefallenbacktoper-directionloopsanyway.

Claude Opus 5.5

Write Python that reads a chess position (FEN) and lists which pieces are under attack. Use TensorFlow for speed. Here’s my design: build an 8×8 tensor board, generate an attack map for each piece type from its movement pattern, and flag opposing pieces on attacked squares. Change anything you think is wrong, and in your final summary explain each change you made and why

Blockedlines(bishops,rooks,queens).Afixedmaskcan’tsay“stopatthefirstpieceintheway.”Iaddedasecondstackofmasksmarkingthesquaresstrictlybetweeneverytwosquaresonthesameline.Onematrixmultiplywiththeboard’soccupancycountstheblockersoneverylineatonce,andanattacksurvivesonlyifthatcountiszero.Knightsandsinglestepshavenothingbetweenthem,soonerulecoverseverypiece

Quote

“Verbose, hard-to-follow output has been my biggest frustration with frontier models, and Claude Opus 5.5 fixes it. It writes like a good colleague, and follows our writing rules. A design spec came out usable with very minimal edits, and when it rewrote one of our prompts I preferred its version to my own. When it optimized our test suite, I could follow its reasoning easily and shipped the change with confidence.”

CompanyRamp
AuthorJohn Ruelas, Staff Software Engineer

Source: www.anthropique.com