Compare / Claude Haiku 4.5 vs Mercury 3
Claude Haiku 4.5 vs Mercury 3
Which is cheaper, which is more capable, and which does better at each kind of work, from 56 results on 4 sources that measured both models.
Of the 56 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 Haiku 4.5 or Mercury 3? The short answer
Pick Mercury 3: it scores higher (Spring Prompt overall 39 against 8) and costs less.
- Spring Prompt overall: Claude Haiku 4.5 8, Mercury 3 39 (out of 100; how the score works).
- Mercury 3 is cheaper to run: $0.012 against $0.046 per deck on DeckBench (4.0 times less).
- Mercury 3 is newer: released 19 Oct 2026, against 15 Oct 2025 for Claude Haiku 4.5.
- On our own benchmarks, on the results both models have: Mercury 3 does better for user surveys, marketing planning and speed under pressure.
Head to head
Every fact side by side
| Claude Haiku 4.5 | Mercury 3 | |
|---|---|---|
| Price per million tokens | $1.00 in · $5.00 out | $0.20 in · $0.70 out |
| Blended (3 in : 1 out) | $2.00 | $0.33 |
| Cheapest host, blended | $2.00 (Amazon Bedrock) | – |
| Cost per deck (DeckBench) | $0.046 | $0.012 |
| Cached input, per million | $0.10 cached input | $0.020 cached input |
| Intelligence Index | 16.9 | – |
| Spring Prompt overall | 8 | 39 |
| Output speed, tokens a second | – | – |
| Context window | 200,000 tokens | 1,000,000 tokens |
| Released | 15 Oct 2025 | 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 Haiku 4.5 | Mercury 3 |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better 23 · 7 of 32 measured | $0.0163 | $0.0020no reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better 18 · 15 of 32 measured | 445 | 491no reasoning |
| Ladder Elo · Lightning 10+1ladder Elo, higher is better 21 · 12 of 24 measured | 33 | 555no reasoning |
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 9 · 4 of 24 measured | $0.0461 | $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. 20 · 18 of 24 measured | 702 | 812 |
| Accurate decks% of tasks, higher is better 17 · 20 of 24 measured | 16.7% | 0.0% |
| ROASBench measured by Spring Prompt · 3 results | ||
| Overall scorescore out of 100, higher is better 23 · 18 of 24 measured | 17.5 | 26.1 |
| Audience scorescore out of 100, higher is better 23 · 21 of 24 measured | 30.9 | 43.2 |
| Business scorescore out of 100, higher is better 23 · 18 of 24 measured | 7.3 | 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. 12 · 9 of 13 measured | 572 | 752 |
| Cost per taskUS dollars, lower is better 5 · 3 of 12 measured | $0.0635 | $0.0216 |
| Analysis scorepoints of 100, higher is better 9 · 12 of 13 measured | 56.8 | 42.2 |
Show all 56 results (44 more)
| Measure | Claude Haiku 4.5 | Mercury 3 |
|---|---|---|
| BulletBench measured by Spring Prompt · 7 results | ||
| Cost per game · Lightning 10+1US dollars, lower is better 19 · 5 of 24 measured | $0.0095 | $0.0010no reasoning |
| Games lost on time · Bullet 60s% of games, lower is better 14 · 1 of 32 measured | 25.0% | 0.0%no reasoning |
| Games lost on time · Lightning 10+1% of games, lower is better 21 · 1 of 24 measured | 83.3% | 0.0%no reasoning |
| Invalid moves · Bullet 60s% of moves, lower is better 26 · 1 of 32 measured | 0.3% | 0.0%low reasoning |
| Invalid moves · Lightning 10+1% of moves, lower is better 1 · 18 of 24 measured | 0.0% | 0.4%no reasoning |
| Median move time · Bullet 60smilliseconds, lower is better 18 · 3 of 32 measured | 1.2 s | 0.4 sno reasoning |
| Median move time · Lightning 10+1milliseconds, lower is better 21 · 3 of 24 measured | 1.3 s | 0.4 sno reasoning |
| DeckBench measured by Spring Prompt · 14 results | ||
| Caveat dropped% of tasks, lower is better 1 · 12 of 24 measured | 0.0% | 16.7% |
| Clean layout% of tasks, higher is better 12 · 6 of 24 measured | 50.0% | 66.7% |
| Design quality% of the maximum, higher is better 20 · 16 of 24 measured | 47.6% | 58.5% |
| Draft figure quoted% of tasks, lower is better 19 · 12 of 24 measured | 50.0% | 33.3% |
| Findings missing% of tasks, lower is better 17 · 17 of 24 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. 20 · 16 of 24 measured | 30.6% | 44.0% |
| Layout defects% of tasks, lower is better 12 · 6 of 24 measured | 50.0% | 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 12 · 12 of 24 measured | 0.0% | 0.0% |
| Recommendation late or wrong% of tasks, lower is better 17 · 22 of 24 measured | 50.0% | 83.3% |
| Slides needing work% of tasks, lower is better 16 · 7 of 24 measured | 66.7% | 33.3% |
| Time per deckseconds, lower is better 4 · 9 of 24 measured | 51.7 | 83.3 |
| Unsupported claims% of tasks, lower is better 17 · 11 of 24 measured | 33.3% | 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 23 · 19 of 24 measured | 8.7 | 15.1 |
| Contribution profitsimulated US dollars, higher is better 24 · 18 of 24 measured | −$205,001 | $104,868 |
| Cost of a runUS dollars, lower is better 3 · 6 of 24 measured | $0.0298 | $0.0533 |
| Months over budgetmonths of 12, lower is better 22 · 1 of 24 measured | 2 | 0 |
| Planning scorescore out of 100, higher is better 19 · 23 of 24 measured | 54.4 | 53.8 |
| Return on ad spendprofit per $1 spent, higher is better 24 · 18 of 24 measured | −$0.21 | $0.10 |
| 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. 12 · 6 of 13 measured | 22.3% | 48.6% |
| Leading or double-barrelled questions% of tasks, lower is better 10 · 8 of 13 measured | 66.7% | 55.6% |
| Mistaken next steps% of tasks, lower is better 10 · 5 of 13 measured | 55.6% | 22.2% |
| Numbers right% of answers, higher is better 12 · 13 of 13 measured | 63.7% | 63.3% |
| Objectives unanswerable% of tasks, lower is better 11 · 1 of 13 measured | 22.2% | 0.0% |
| Precision ignored% of tasks, lower is better 11 · 1 of 13 measured | 100.0% | 0.0% |
| Research scorepoints of 100, higher is better 9 · 11 of 13 measured | 64.9 | 56.8 |
| Sound research% of tasks, higher is better 6 · 6 of 13 measured | 0.0% | 0.0% |
| Stakeholder's view presumed% of tasks, lower is better 7 · 7 of 13 measured | 22.2% | 22.2% |
| Survey plan scorepoints of 100, higher is better 9 · 6 of 13 measured | 83.6 | 90.8 |
| Survey structure% of tasks, lower is better 1 · 7 of 13 measured | 0.0% | 22.2% |
| Time per taskseconds, lower is better 5 · 10 of 12 measured | 92.6 | 194 |
| Traps handled% of traps, higher is better 10 · 11 of 13 measured | 62.3% | 60.7% |
| Traps missed% of tasks, lower is better 7 · 7 of 13 measured | 88.9% | 88.9% |
| Unsupported findings% of tasks, lower is better 10 · 4 of 13 measured | 100.0% | 44.4% |
| Wrong numbers% of tasks, lower is better 11 · 9 of 13 measured | 100.0% | 44.4% |
| Wrong recommendation% of tasks, lower is better 8 · 12 of 13 measured | 44.4% | 77.8% |
Compare them with other models
Quick answers
Is Claude Haiku 4.5 better than Mercury 3?
Pick Mercury 3: it scores higher (Spring Prompt overall 39 against 8) and costs less.
Which is cheaper, Claude Haiku 4.5 or Mercury 3?
Mercury 3 is cheaper to run: $0.012 against $0.046 per deck on DeckBench (4.0 times less).
Which is better for decks from an analysis, Claude Haiku 4.5 or Mercury 3?
Mercury 3 ranks 18 of 24 models on sale for turning a finished analysis into a deck you could present as it is, against 20 for Claude Haiku 4.5.
Which is better for user surveys, Claude Haiku 4.5 or Mercury 3?
Mercury 3 ranks 9 of 13 models on sale for planning a user survey and reading its results without being misled, against 12 for Claude Haiku 4.5.
Which is better for marketing planning, Claude Haiku 4.5 or Mercury 3?
Mercury 3 ranks 18 of 24 models on sale for planning a year of ad spend without overspending, against 23 for Claude Haiku 4.5.
Which is better for speed under pressure, Claude Haiku 4.5 or Mercury 3?
Mercury 3 ranks 10 of 27 models on sale for good decisions against a real clock (fast chess), against 19 for Claude Haiku 4.5.
Which has the bigger context window, Claude Haiku 4.5 or Mercury 3?
Mercury 3: 1,000,000 tokens, against 200,000 for Claude Haiku 4.5.
Run Claude Haiku 4.5 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.