Compare / Claude Fable 5.2 vs Mercury 3

Claude Fable 5.2 vs Mercury 3

Which is cheaper, which is more capable, and which does better at each kind of work, from 53 results on 4 sources that measured both models.

AnthropicClaude Fable 5.2 Released 9 Nov 2026 · $8.00 in · $40.00 out
InceptionMercury 3 Released 19 Oct 2026 · Not on sale
Claude Fable 5.2 wins 3410 too close to callMercury 3 wins 9

Of the 53 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 Fable 5.2 or Mercury 3? The short answer

Pick Claude Fable 5.2 if quality matters most: it scores higher (Spring Prompt overall 88 against 33). Pick Mercury 3 if cost matters more: it costs 120 times less per deck on DeckBench.

  • Spring Prompt overall: Claude Fable 5.2 88, Mercury 3 33 (out of 100; how the score works).
  • Mercury 3 is cheaper to run: $0.012 against $1.40 per deck on DeckBench (120 times less).
  • Claude Fable 5.2 is newer: released 9 Nov 2026, against 19 Oct 2026 for Mercury 3.
  • On our own benchmarks, on the results both models have: Claude Fable 5.2 does better for decks from an analysis, user surveys and marketing planning.

Head to head

88
Spring Prompt overall
33

Every fact side by side

Claude Fable 5.2Mercury 3
Price per million tokens$8.00 in · $40.00 outNot on sale
Blended (3 in : 1 out)$16.00–
Cheapest host, blended$16.00 (Amazon Bedrock)–
Cost per deck (DeckBench)$1.40$0.012
Cached input, per million$0.20 cached input–
Intelligence Index––
Spring Prompt overall8833
Output speed, tokens a second––
Context window1,000,000 tokens–
Released9 Nov 2026 (newer)19 Oct 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 8 of 35 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 4 of 35 30 of 36
User surveysPlanning a user survey and reading its results without being misled 1 of 26 21 of 27
Marketing planningPlanning a year of ad spend without overspending 1 of 35 30 of 36
Speed under pressureGood decisions against a real clock (fast chess) 10 of 38 16 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 Fable 5.2's deck for Hearthside Coffee
Claude Fable 5.2 · deck rating 1,403 · needs work
First slide of Mercury 3's deck for Hearthside Coffee
Mercury 3 · deck rating 726 · needs work

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 Fable 5.2Mercury 3
BulletBench measured by Spring Prompt · 3 results
Cost per game · Bullet 60sUS dollars, lower is better 60 · 24 of 62 measured $0.0800low reasoning $0.0020no reasoning
Ladder Elo · Bullet 60sladder Elo, higher is better 33 · 33 of 62 measured 491 491no reasoning
Games lost on time · Bullet 60s% of games, lower is better 47 · 1 of 62 measured 62.5% 0.0%no reasoning
DeckBench measured by Spring Prompt · 3 results
Cost per deckUS dollars, lower is better 36 · 6 of 36 measured $1.40 $0.0116
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. 4 · 30 of 36 measured 1,403 726
Accurate decks% of tasks, higher is better 6 · 31 of 36 measured 83.3% 0.0%
ROASBench measured by Spring Prompt · 3 results
Overall scorescore out of 100, higher is better 1 · 30 of 36 measured 61.3 26.1
Audience scorescore out of 100, higher is better 5 · 33 of 36 measured 68.5 43.2
Business scorescore out of 100, higher is better 1 · 30 of 36 measured 72.3 17.6
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. 1 · 21 of 27 measured 1,670 735
Cost per taskUS dollars, lower is better 27 · 7 of 27 measured $1.51 $0.0216
Analysis scorepoints of 100, higher is better 1 · 24 of 27 measured 98.0 42.2
Show all 53 results (41 more)
MeasureClaude Fable 5.2Mercury 3
BulletBench measured by Spring Prompt · 2 results
Invalid moves · Bullet 60s% of moves, lower is better 1 · 1 of 62 measured 0.0% 0.0%low reasoning
Median move time · Bullet 60smilliseconds, lower is better 55 · 3 of 62 measured 3.0 slow reasoning 0.4 sno reasoning
DeckBench measured by Spring Prompt · 15 results
Caveat dropped% of tasks, lower is better 16 · 16 of 36 measured 16.7% 16.7%
Clean layout% of tasks, higher is better 5 · 10 of 36 measured 83.3% 66.7%
Design quality% of the maximum, higher is better 11 · 25 of 36 measured 77.8% 58.5%
Draft figure quoted% of tasks, lower is better 15 · 21 of 36 measured 16.7% 33.3%
Findings missing% of tasks, lower is better 25 · 25 of 36 measured 16.7% 16.7%
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. 12 · 30 of 36 measured 69.7% 35.2%
Layout defects% of tasks, lower is better 5 · 10 of 36 measured 16.7% 33.3%
Misleading metric used% of tasks, lower is better 31 · 31 of 36 measured 16.7% 16.7%
Output tokens per decktokens, lower is better 11 · 10 of 15 measured 33,285 32,448
Presentable decks% of tasks, higher is better 2 · 17 of 36 measured 83.3% 0.0%
Recommendation late or wrong% of tasks, lower is better 17 · 33 of 36 measured 16.7% 83.3%
Slides needing work% of tasks, lower is better 5 · 12 of 36 measured 16.7% 33.3%
Time per deckseconds, lower is better 28 · 12 of 36 measured 285 83.3
Unsupported claims% of tasks, lower is better 17 · 17 of 36 measured 16.7% 16.7%
Unsupported numbers% of tasks, lower is better 28 · 28 of 36 measured 16.7% 16.7%
ROASBench measured by Spring Prompt · 6 results
Consistency scorescore out of 100, higher is better 16 · 31 of 36 measured 31.6 15.1
Contribution profitsimulated US dollars, higher is better 1 · 30 of 36 measured $1,032,894 $104,868
Cost of a runUS dollars, lower is better 35 · 8 of 36 measured $1.76 $0.0533
Months over budgetmonths of 12, lower is better 1 · 1 of 36 measured 0 0
Planning scorescore out of 100, higher is better 31 · 35 of 36 measured 54.2 53.8
Return on ad spendprofit per $1 spent, higher is better 1 · 30 of 36 measured $0.96 $0.10
SurveyBench measured by Spring Prompt · 18 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. 1 · 18 of 27 measured 87.5% 42.4%
Leading or double-barrelled questions% of tasks, lower is better 10 · 21 of 27 measured 22.2% 55.6%
Mistaken next steps% of tasks, lower is better 1 · 13 of 27 measured 0.0% 22.2%
Numbers right% of answers, higher is better 1 · 27 of 27 measured 100.0% 63.3%
Objectives unanswerable% of tasks, lower is better 1 · 1 of 27 measured 0.0% 0.0%
Output tokens per tasktokens, lower is better 9 · 15 of 17 measured 33,902 57,343
Precision ignored% of tasks, lower is better 1 · 1 of 27 measured 0.0% 0.0%
Research scorepoints of 100, higher is better 1 · 23 of 27 measured 97.6 56.8
Sound research% of tasks, higher is better 5 · 17 of 27 measured 44.4% 0.0%
Stakeholder's view presumed% of tasks, lower is better 1 · 18 of 27 measured 0.0% 22.2%
Survey plan scorepoints of 100, higher is better 5 · 18 of 27 measured 96.9 90.8
Survey structure% of tasks, lower is better 3 · 12 of 27 measured 11.1% 22.2%
Time per taskseconds, lower is better 20 · 16 of 27 measured 337 194
Traps handled% of traps, higher is better 3 · 25 of 27 measured 98.6% 60.7%
Traps missed% of tasks, lower is better 2 · 19 of 27 measured 11.1% 88.9%
Unsupported findings% of tasks, lower is better 4 · 11 of 27 measured 11.1% 44.4%
Wrong numbers% of tasks, lower is better 1 · 21 of 27 measured 0.0% 44.4%
Wrong recommendation% of tasks, lower is better 1 · 24 of 27 measured 0.0% 77.8%

Quick answers

Is Claude Fable 5.2 better than Mercury 3?

Pick Claude Fable 5.2 if quality matters most: it scores higher (Spring Prompt overall 88 against 33). Pick Mercury 3 if cost matters more: it costs 120 times less per deck on DeckBench.

Which is cheaper, Claude Fable 5.2 or Mercury 3?

Mercury 3 is cheaper to run: $0.012 against $1.40 per deck on DeckBench (120 times less).

Which is better for decks from an analysis, Claude Fable 5.2 or Mercury 3?

Claude Fable 5.2 ranks 4 of 35 models on sale for turning a finished analysis into a deck you could present as it is, against 30 for Mercury 3.

Which is better for user surveys, Claude Fable 5.2 or Mercury 3?

Claude Fable 5.2 ranks 1 of 26 models on sale for planning a user survey and reading its results without being misled, against 21 for Mercury 3.

Which is better for marketing planning, Claude Fable 5.2 or Mercury 3?

Claude Fable 5.2 ranks 1 of 35 models on sale for planning a year of ad spend without overspending, against 30 for Mercury 3.

Which is better for speed under pressure, Claude Fable 5.2 or Mercury 3?

Claude Fable 5.2 ranks 10 of 38 models on sale for good decisions against a real clock (fast chess), against 16 for Mercury 3.

Run Claude Fable 5.2 and Mercury 3 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.