Compare / Claude Haiku 5.5 vs Claude Opus 5.5

Claude Haiku 5.5 vs Claude Opus 5.5

Which is cheaper, which is more capable, and which does better at each kind of work, from 89 results on 6 sources that measured both models.

AnthropicClaude Haiku 5.5 Released 7 Oct 2026 · $0.10 in · $0.50 out
AnthropicClaude Opus 5.5 Released 22 Sep 2026 · $4.00 in · $20.00 out
Claude Haiku 5.5 wins 1816 too close to callClaude Opus 5.5 wins 55

Of the 89 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

Claude Haiku 5.5 or Claude Opus 5.5? The short answer

Pick Claude Opus 5.5 if quality matters most: it scores higher (Spring Prompt overall 80 against 38). Pick Claude Haiku 5.5 if cost matters more: it costs 33 times less per product listing on CatalogBench. Claude Haiku 5.5 is also faster.

  • Spring Prompt overall: Claude Haiku 5.5 38, Claude Opus 5.5 80 (out of 100; how the score works).
  • Claude Haiku 5.5 is cheaper to run: $0.001 against $0.040 per product listing on CatalogBench (33 times less).
  • Claude Opus 5.5 scores higher on the Artificial Analysis Intelligence Index: 57.6 against 43.4.
  • Claude Haiku 5.5 writes faster: 240 tokens a second against 96.
  • Claude Haiku 5.5 is newer: released 7 Oct 2026, against 22 Sep 2026 for Claude Opus 5.5.
  • On our own benchmarks, on the results both models have: Claude Opus 5.5 does better for product listings, decks from an analysis, user surveys and marketing planning.
  • On third-party benchmarks, on the results both models have: Claude Opus 5.5 does better for agents and tool use and reasoning and knowledge.

Head to head

38
Spring Prompt overall
80
43.4
Intelligence Index
57.6
$0.20
Price per million tokens, blendedlower is better
$8.00
240
Output speed, tokens a second
96
1,000,000
Context window, tokens
1,000,000

Every fact side by side

Claude Haiku 5.5Claude Opus 5.5
Price per million tokens$0.10 in · $0.50 out$4.00 in · $20.00 out
Blended (3 in : 1 out)$0.20$8.00
Cheapest host, blended$0.20 (Amazon Bedrock)$8.00 (Amazon Bedrock)
Cost per product listing (CatalogBench)$0.001$0.040
Cached input, per million–$0.20 cached input
Intelligence Index43.457.6
Spring Prompt overall3880
Output speed, tokens a second24096
Context window1,000,000 tokens1,000,000 tokens
Released7 Oct 2026 (newer)22 Sep 2026
WeightsClosedClosed
Developer based inthe USthe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Product listingsTurning a sparse product feed and photos into listings that can go live 23 of 35 16 of 35
Decks from an analysisTurning a finished analysis into a deck you could present as it is 19 of 35 8 of 35
User surveysPlanning a user survey and reading its results without being misled 9 of 26 5 of 26
Marketing planningPlanning a year of ad spend without overspending 33 of 35 11 of 35
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 28 of 159 3 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 3 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge 25 of 187 1 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality not measured 5 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 3 of 139
Speed under pressureGood decisions against a real clock (fast chess) 24 of 38 39 of 39

Their slides, side by side

The same brief for both: Manchester store investment review for Hearthside Coffee, an invented company. First slide of each deck from DeckBench.

First slide of Claude Haiku 5.5's deck for Hearthside Coffee
Claude Haiku 5.5 · deck rating 1,120 · needs work
First slide of Claude Opus 5.5's deck for Hearthside Coffee
Claude Opus 5.5 · deck rating 1,323 · presentable as it is

Every slide, side by side →

From our research

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureClaude Haiku 5.5Claude Opus 5.5
BulletBench measured by Spring Prompt · 3 results
Cost per game · Blitz 3+2US dollars, lower is better 4 · 16 of 23 measured $0.0164 $0.18
Games lost on time · Blitz 3+2% of games, lower is better 11 · 20 of 23 measured 37.5% 62.5%
Invalid moves · Blitz 3+2% of moves, lower is better 1 · 1 of 23 measured 0.0% 0.0%
CatalogBench measured by Spring Prompt · 3 results
Cost per productUS dollars, lower is better 4 · 31 of 36 measured $0.0012 $0.0400
Reliably publish-ready% of products, higher is better 26 · 13 of 35 measured 26.8% 55.4%
Reliably publish-ready · sales brief% of products, higher is better 20 · 16 of 35 measured 10.7% 21.4%
DeckBench measured by Spring Prompt · 3 results
Cost per deckUS dollars, lower is better 4 · 30 of 36 measured $0.0091 $0.26
Deck ratingrating, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 19 · 8 of 36 measured 1,120 1,323
Accurate decks% of tasks, higher is better 22 · 6 of 36 measured 33.3% 83.3%
ROASBench measured by Spring Prompt · 3 results
Overall scorescore out of 100, higher is better 34 · 11 of 36 measured 24.1 51.7
Audience scorescore out of 100, higher is better 30 · 9 of 36 measured 48.4 67.7
Business scorescore out of 100, higher is better 32 · 10 of 36 measured 13.5 52.3
SurveyBench measured by Spring Prompt · 3 results
Analysis ratingrating, higher is betterThe rating weighs each win by how strong the other analysis was; the win rate counts wins against whichever analyses a model happened to meet, so the two can disagree. 9 · 5 of 27 measured 1,233 1,417
Cost per taskUS dollars, lower is better 4 · 24 of 27 measured $0.0185 $0.46
Analysis scorepoints of 100, higher is better 11 · 5 of 27 measured 88.4 95.3
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 20 · 1 of 249 measured 43.4max reasoning 57.6max reasoning
Humanity's Last Exam% of questions, higher is better 25 · 1 of 250 measured 44.4%max reasoning 61.4%max reasoning
Terminal-Bench 4.0% of tasks, higher is better 20 · 3 of 120 measured 32.8%max reasoning 59.6%max reasoning
Show all 89 results (71 more)
MeasureClaude Haiku 5.5Claude Opus 5.5
BulletBench measured by Spring Prompt · 2 results
Ladder Elo · Blitz 3+2ladder Elo, higher is better 14 · 14 of 23 measured 557 557
Median move time · Blitz 3+2milliseconds, lower is better 16 · 21 of 23 measured 6.2 s 7.5 s
CatalogBench measured by Spring Prompt · 28 results
Channel compliance% of products, higher is better 1 · 1 of 36 measured 100.0% 100.0%
Channel rules broken% of products, lower is better 22 · 1 of 36 measured 0.6% 0.0%
Channel rules broken · sales brief% of products, lower is better 1 · 19 of 36 measured 0.0% 0.6%
Claims to check% of products, lower is better 25 · 1 of 34 measured 0.6% 0.0%
Claims to check · sales brief% of products, lower is better 24 · 1 of 34 measured 1.2% 0.0%
Conflicts caught% of conflicts, higher is better 1 · 1 of 36 measured 100.0% 100.0%
Content quality% of checks, higher is better 29 · 9 of 36 measured 95.6% 97.9%
Content quality · sales brief% of checks, higher is better 24 · 15 of 36 measured 96.3% 97.8%
Decision accuracy% of decisions, higher is better 28 · 11 of 36 measured 95.6% 97.7%
Failed outputs% of products, lower is better 1 · 1 of 36 measured 0.0% 0.0%
Failed outputs · sales brief% of products, lower is better 1 · 1 of 36 measured 0.0% 0.0%
Field accuracy% of missing fields, higher is better 34 · 31 of 36 measured 91.0% 92.2%
Invented values% of filled values, lower is better 11 · 6 of 36 measured 0.8% 0.5%
Missing UK information% of products, lower is better 1 · 1 of 36 measured 0.0% 0.0%
Missing UK information · sales brief% of products, lower is better 1 · 1 of 36 measured 0.0% 0.0%
Not findable% of products, lower is better 34 · 10 of 36 measured 11.9% 3.0%
Not findable · sales brief% of products, lower is better 34 · 5 of 36 measured 10.7% 1.8%
Publish-ready listings% of products, higher is better 26 · 13 of 36 measured 47.0% 70.8%
Publish-ready listings · sales brief% of products, higher is better 24 · 18 of 36 measured 20.2% 34.5%
Time per productseconds, lower is better 16 · 18 of 36 measured 11.0 16.9
Unsupported claimsclaims per product, lower is better 31 · 18 of 36 measured 1.20 0.45
Unsupported claims% of products, lower is better 28 · 20 of 36 measured 32.1% 17.3%
Unsupported claims · sales briefclaims per product, lower is better 25 · 19 of 36 measured 2.46 1.66
Unsupported claims · sales brief% of products, lower is better 25 · 21 of 36 measured 70.2% 60.1%
Wrong attributes% of products, lower is better 26 · 14 of 36 measured 19.6% 15.5%
Wrong attributes · sales brief% of products, lower is better 22 · 15 of 36 measured 18.5% 15.5%
Wrong category or variant% of products, lower is better 1 · 7 of 36 measured 0.0% 1.8%
Wrong category or variant · sales brief% of products, lower is better 1 · 7 of 36 measured 0.0% 1.8%
DeckBench measured by Spring Prompt · 14 results
Caveat dropped% of tasks, lower is better 16 · 16 of 36 measured 16.7% 16.7%
Clean layout% of tasks, higher is better 10 · 5 of 36 measured 66.7% 83.3%
Design quality% of the maximum, higher is better 22 · 13 of 36 measured 61.1% 72.0%
Draft figure quoted% of tasks, lower is better 21 · 1 of 36 measured 33.3% 0.0%
Findings missing% of tasks, lower is better 25 · 1 of 36 measured 16.7% 0.0%
Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other deck was; the win rate counts wins against whichever decks a model happened to meet, so the two can disagree. 15 · 5 of 36 measured 62.1% 79.7%
Layout defects% of tasks, lower is better 10 · 5 of 36 measured 33.3% 16.7%
Misleading metric used% of tasks, lower is better 31 · 1 of 36 measured 16.7% 0.0%
Presentable decks% of tasks, higher is better 9 · 9 of 36 measured 33.3% 33.3%
Recommendation late or wrong% of tasks, lower is better 22 · 1 of 36 measured 33.3% 0.0%
Slides needing work% of tasks, lower is better 5 · 26 of 36 measured 16.7% 66.7%
Time per deckseconds, lower is better 7 · 16 of 36 measured 62.1 98.5
Unsupported claims% of tasks, lower is better 26 · 1 of 36 measured 33.3% 0.0%
Unsupported numbers% of tasks, lower is better 28 · 1 of 36 measured 16.7% 0.0%
ROASBench measured by Spring Prompt · 6 results
Consistency scorescore out of 100, higher is better 33 · 13 of 36 measured 10.6 33.8
Contribution profitsimulated US dollars, higher is better 32 · 3 of 36 measured $32,146 $911,566
Cost of a runUS dollars, lower is better 6 · 31 of 36 measured $0.0313 $1.06
Months over budgetmonths of 12, lower is better 1 · 1 of 36 measured 0 0
Planning scorescore out of 100, higher is better 21 · 24 of 36 measured 54.8 54.7
Return on ad spendprofit per $1 spent, higher is better 32 · 6 of 36 measured $0.03 $0.69
SurveyBench measured by Spring Prompt · 17 results
Head-to-head win rate% of comparisons, higher is betterThe rating weighs each win by how strong the other analysis was; the win rate counts wins against whichever analyses a model happened to meet, so the two can disagree. 8 · 2 of 27 measured 59.9% 76.0%
Leading or double-barrelled questions% of tasks, lower is better 12 · 1 of 27 measured 33.3% 0.0%
Mistaken next steps% of tasks, lower is better 13 · 1 of 27 measured 22.2% 0.0%
Numbers right% of answers, higher is better 1 · 1 of 27 measured 100.0% 100.0%
Objectives unanswerable% of tasks, lower is better 1 · 1 of 27 measured 0.0% 0.0%
Precision ignored% of tasks, lower is better 1 · 1 of 27 measured 0.0% 0.0%
Research scorepoints of 100, higher is better 10 · 4 of 27 measured 90.2 96.1
Sound research% of tasks, higher is better 13 · 4 of 27 measured 11.1% 55.6%
Stakeholder's view presumed% of tasks, lower is better 1 · 1 of 27 measured 0.0% 0.0%
Survey plan scorepoints of 100, higher is better 8 · 1 of 27 measured 94.5 97.8
Survey structure% of tasks, lower is better 12 · 3 of 27 measured 22.2% 11.1%
Time per taskseconds, lower is better 13 · 15 of 27 measured 147 180
Traps handled% of traps, higher is better 11 · 8 of 27 measured 94.2% 95.7%
Traps missed% of tasks, lower is better 4 · 8 of 27 measured 22.2% 33.3%
Unsupported findings% of tasks, lower is better 16 · 7 of 27 measured 77.8% 22.2%
Wrong numbers% of tasks, lower is better 1 · 1 of 27 measured 0.0% 0.0%
Wrong recommendation% of tasks, lower is better 5 · 1 of 27 measured 11.1% 0.0%
Artificial Analysis reported by Artificial Analysis · 4 results
Long-context reasoning (AA-LCR)% of questions, higher is better 21 · 5 of 241 measured 82.7%max reasoning 84.7%max reasoning
Output speedtokens per second, higher is better 10 · 46 of 78 measured 240max reasoning 96.0max reasoning
SciCode% of problems, higher is better 28 · 1 of 121 measured 55.0%max reasoning 66.9%max reasoning
Time to first answer tokenseconds, lower is better 40 · 43 of 78 measured 6.41low reasoning 6.89low reasoning

Quick answers

Is Claude Haiku 5.5 better than Claude Opus 5.5?

Pick Claude Opus 5.5 if quality matters most: it scores higher (Spring Prompt overall 80 against 38). Pick Claude Haiku 5.5 if cost matters more: it costs 33 times less per product listing on CatalogBench. Claude Haiku 5.5 is also faster.

Which is cheaper, Claude Haiku 5.5 or Claude Opus 5.5?

Claude Haiku 5.5 is cheaper to run: $0.001 against $0.040 per product listing on CatalogBench (33 times less).

Which is faster, Claude Haiku 5.5 or Claude Opus 5.5?

Claude Haiku 5.5 writes about 240 tokens a second on its usual API, against 96 for Claude Opus 5.5 (Artificial Analysis).

Which is better for product listings, Claude Haiku 5.5 or Claude Opus 5.5?

Claude Opus 5.5 ranks 16 of 35 models on sale for turning a sparse product feed and photos into listings that can go live, against 23 for Claude Haiku 5.5.

Which is better for decks from an analysis, Claude Haiku 5.5 or Claude Opus 5.5?

Claude Opus 5.5 ranks 8 of 35 models on sale for turning a finished analysis into a deck you could present as it is, against 19 for Claude Haiku 5.5.

Which is better for user surveys, Claude Haiku 5.5 or Claude Opus 5.5?

Claude Opus 5.5 ranks 5 of 26 models on sale for planning a user survey and reading its results without being misled, against 9 for Claude Haiku 5.5.

Which is better for marketing planning, Claude Haiku 5.5 or Claude Opus 5.5?

Claude Opus 5.5 ranks 11 of 35 models on sale for planning a year of ad spend without overspending, against 33 for Claude Haiku 5.5.

Run Claude Haiku 5.5 and Claude Opus 5.5 on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.