Compare / Claude Sonnet 5.5 vs Mercury 3
Claude Sonnet 5.5 vs Mercury 3
Which is cheaper, which is more capable, and which does better at each kind of work, from 31 results on 3 sources that measured both models.
Of the 31 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 20 October 2026 (catalogue release 2026-10-20-96eb40c3ec63).
Claude Sonnet 5.5 or Mercury 3? The short answer
Pick Claude Sonnet 5.5 if quality matters most: it scores higher (Spring Prompt overall 63 against 39). Pick Mercury 3 if cost matters more: it costs 13 times less per deck on DeckBench.
- Spring Prompt overall: Claude Sonnet 5.5 63, Mercury 3 39 (out of 100; how the score works).
- Mercury 3 is cheaper to run: $0.012 against $0.15 per deck on DeckBench (13 times less).
- Mercury 3 is newer: released 19 Oct 2026, against 28 Sep 2026 for Claude Sonnet 5.5.
- On our own benchmarks, on the results both models have: Claude Sonnet 5.5 does better for decks from an analysis and marketing planning.
Head to head
Every fact side by side
| Claude Sonnet 5.5 | Mercury 3 | |
|---|---|---|
| Price per million tokens | $2.00 in · $10.00 out | $0.20 in · $0.70 out |
| Blended (3 in : 1 out) | $4.00 | $0.33 |
| Cheapest host, blended | $4.00 (Amazon Bedrock) | – |
| Cost per deck (DeckBench) | $0.15 | $0.012 |
| Cached input, per million | $0.20 cached input | $0.020 cached input |
| Intelligence Index | 56.0 | – |
| Spring Prompt overall | 63 | 39 |
| Output speed, tokens a second | 137 | – |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Released | 28 Sep 2026 | 19 Oct 2026 (newer) |
| Weights | Closed | Closed |
| Developer based in | the US | the 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.
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.
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.
| Measure | Claude Sonnet 5.5 | Mercury 3 |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Ladder Elo · Lightning 10+1ladder Elo, higher is better 21 · 12 of 24 measured | 33low reasoning | 555no reasoning |
| Cost per game · Lightning 10+1US dollars, lower is better 18 · 5 of 24 measured | $0.0080low reasoning | $0.0010no reasoning |
| Games lost on time · Lightning 10+1% of games, lower is better 23 · 1 of 24 measured | 91.7%low reasoning | 0.0%no reasoning |
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 16 · 4 of 24 measured | $0.15 | $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. 5 · 18 of 24 measured | 1,408 | 812 |
| Accurate decks% of tasks, higher is better 6 · 20 of 24 measured | 66.7% | 0.0% |
| ROASBench measured by Spring Prompt · 3 results | ||
| Overall scorescore out of 100, higher is better 4 · 18 of 24 measured | 52.0 | 26.1 |
| Audience scorescore out of 100, higher is better 11 · 21 of 24 measured | 61.8 | 43.2 |
| Business scorescore out of 100, higher is better 2 · 18 of 24 measured | 57.2 | 17.6 |
Show all 31 results (22 more)
| Measure | Claude Sonnet 5.5 | Mercury 3 |
|---|---|---|
| BulletBench measured by Spring Prompt · 2 results | ||
| Invalid moves · Lightning 10+1% of moves, lower is better 1 · 18 of 24 measured | 0.0%low reasoning | 0.4%no reasoning |
| Median move time · Lightning 10+1milliseconds, lower is better 24 · 3 of 24 measured | 2.1 slow reasoning | 0.4 sno reasoning |
| DeckBench measured by Spring Prompt · 14 results | ||
| Caveat dropped% of tasks, lower is better 12 · 12 of 24 measured | 16.7% | 16.7% |
| Clean layout% of tasks, higher is better 1 · 6 of 24 measured | 100.0% | 66.7% |
| Design quality% of the maximum, higher is better 4 · 16 of 24 measured | 78.5% | 58.5% |
| Draft figure quoted% of tasks, lower is better 1 · 12 of 24 measured | 0.0% | 33.3% |
| Findings missing% of tasks, lower is better 1 · 17 of 24 measured | 0.0% | 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. 4 · 16 of 24 measured | 85.6% | 44.0% |
| Layout defects% of tasks, lower is better 1 · 6 of 24 measured | 0.0% | 33.3% |
| Misleading metric used% of tasks, lower is better 1 · 22 of 24 measured | 0.0% | 16.7% |
| Presentable decks% of tasks, higher is better 2 · 12 of 24 measured | 50.0% | 0.0% |
| Recommendation late or wrong% of tasks, lower is better 9 · 22 of 24 measured | 16.7% | 83.3% |
| Slides needing work% of tasks, lower is better 7 · 7 of 24 measured | 33.3% | 33.3% |
| Time per deckseconds, lower is better 10 · 9 of 24 measured | 83.4 | 83.3 |
| Unsupported claims% of tasks, lower is better 1 · 11 of 24 measured | 0.0% | 16.7% |
| Unsupported numbers% of tasks, lower is better 1 · 20 of 24 measured | 0.0% | 16.7% |
| ROASBench measured by Spring Prompt · 6 results | ||
| Consistency scorescore out of 100, higher is better 10 · 19 of 24 measured | 28.5 | 15.1 |
| Contribution profitsimulated US dollars, higher is better 11 · 18 of 24 measured | $571,203 | $104,868 |
| Cost of a runUS dollars, lower is better 16 · 6 of 24 measured | $0.42 | $0.0533 |
| Months over budgetmonths of 12, lower is better 1 · 1 of 24 measured | 0 | 0 |
| Planning scorescore out of 100, higher is better 3 · 23 of 24 measured | 55.1 | 53.8 |
| Return on ad spendprofit per $1 spent, higher is better 1 · 18 of 24 measured | $0.70 | $0.10 |
Compare them with other models
- Claude Sonnet 5.5 vs Claude Opus 5.5Most intelligent at $3–10 per million tokens
- Claude Sonnet 5.5 vs Muse WonderFastest with similar intelligence
- Claude Sonnet 5.5 vs Claude Fable 5.1Just above overall
- Claude Sonnet 5.5 vs Muse Spark 1.3Just below overall
- Mercury 3 vs Claude Opus 5.5Highest-scoring overall available today
- Mercury 3 vs GPT-6 LunaJust above overall
- Mercury 3 vs GLM-5.3Just below overall
Quick answers
Is Claude Sonnet 5.5 better than Mercury 3?
Pick Claude Sonnet 5.5 if quality matters most: it scores higher (Spring Prompt overall 63 against 39). Pick Mercury 3 if cost matters more: it costs 13 times less per deck on DeckBench.
Which is cheaper, Claude Sonnet 5.5 or Mercury 3?
Mercury 3 is cheaper to run: $0.012 against $0.15 per deck on DeckBench (13 times less).
Which is better for decks from an analysis, Claude Sonnet 5.5 or Mercury 3?
Claude Sonnet 5.5 ranks 5 of 24 models on sale for turning a finished analysis into a deck you could present as it is, against 18 for Mercury 3.
Which is better for marketing planning, Claude Sonnet 5.5 or Mercury 3?
Claude Sonnet 5.5 ranks 4 of 24 models on sale for planning a year of ad spend without overspending, against 18 for Mercury 3.
Which is better for speed under pressure, Claude Sonnet 5.5 or Mercury 3?
Mercury 3 ranks 10 of 27 models on sale for good decisions against a real clock (fast chess), against 24 for Claude Sonnet 5.5.
Run Claude Sonnet 5.5 and Mercury 3 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.