Models / Mercury 3

Inception

Mercury 3

Mercury 3 is strongest at speed under pressure; it is not on sale through OpenRouter, so it is here for reference.

Results 19 Nov 2026 · 63 results · 4 sources

Price per million tokens
Not available through OpenRouter
Speed
Not measured
Intelligence Index
Not measured
Spring Prompt overall
31st of 39 score 33 of 100 · how it works
Spring Prompt Score
32 of 100 29th of 35 · 4 of 5 benchmarks · our own tests only
Developer
Inception, based in the US
Weights not published
Released
19 Oct 2026

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today – 31st of 39Claude Fable 5.2 – –
Models from developers based in the US – 23rd of 25Claude Fable 5.2 – –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

Measured cost per task

API cost recorded in our benchmark runs, excluding judging.

TaskBenchmarkCost per task
DeckDeckBench≈ $0.012
Survey plan and analysisSurveyBench≈ $0.022
Game of bullet chessBulletBench≈ $0.002

Cheapest model that passes

On our benchmarks that define a pass for each task: what one passing answer cost in our run, failed attempts included, and whether a cheaper model passed.

  • DeckBench · cost per presentable deck
    Mercury 3: no presentable decks (0 of 6 tasks). Cheapest: GPT-6.2 Sol at $0.09 (5 of 6 tasks).
  • SurveyBench · cost per sound survey task
    Mercury 3: no sound survey tasks (0 of 9 tasks). Cheapest: GPT-6 Luna at $0.03 (3 of 9 tasks).

Cost per attempt divided by the share that passed, at the run date's prices, excluding judging. Each model at its cheapest setting per passing answer. With a handful of tasks, a pass or two either way is within chance. No estimate where a run had missing outputs, because their cost may not have been recorded.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is 30th of 36 available
BenchmarkMercury 3Rank among availableBest available
DeckBenchDeckBench: deck rating 726 30th of 36 Qwen4-Max 1,563
User surveysPlanning a user survey and reading its results without being misled 21st of 27 available
BenchmarkMercury 3Rank among availableBest available
SurveyBenchSurveyBench: analysis rating 735 21st of 27 Claude Fable 5.2 1,670
Marketing planningPlanning a year of ad spend without overspending 30th of 36 available
BenchmarkMercury 3Rank among availableBest available
ROASBenchROASBench: overall score 26.1 30th of 36 Claude Fable 5.2 61.3
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls PendingReleased after these sources last updated
  • tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
  • Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
  • Artificial Analysis: has not measured this model.
  • Vending-Bench 2: pending. Its latest results are dated 1 Oct 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects PendingReleased after these sources last updated
  • APEX-Agents: pending. Its latest results are dated 1 Oct 2026, before this model was released.
  • GDP.pdf: pending. Its latest results are dated 1 Oct 2026, before this model was released.
  • Remote Labor Index: pending. Its latest results are dated 1 Oct 2026, before this model was released.
Reasoning and knowledgeHard questions across science, maths and general knowledge Not measured
  • Artificial Analysis: has not measured this model.
WritingWhat people prefer in blind comparisons, and judged writing quality PendingReleased after these sources last updated
  • Arena (formerly LMArena): pending. Its latest results are dated 2 Oct 2026, before this model was released.
  • UGI Leaderboard: pending. Its latest results are dated 2 Oct 2026, before this model was released.
Sticking to the factsSummarising without inventing things, and factual answers PendingReleased after these sources last updated
  • Vectara Hallucination Leaderboard: pending. Its latest results are dated 22 Sep 2026, before this model was released.
  • Arena (formerly LMArena): pending. Its latest results are dated 2 Oct 2026, before this model was released.
  • SimpleQA Verified (Epoch AI): pending. Its latest results are dated 29 Sep 2026, before this model was released.
Speed under pressureGood decisions against a real clock (fast chess) 16th of 39 available
BenchmarkMercury 3Rank among availableBest available
BulletBenchBulletBench Lightning 10+1: ladder Elo 555 10th of 19 Gemini 3.5 Flash-Lite 892
BulletBenchBulletBench Bullet 60s: ladder Elo 491 13th of 37 Gemini 3.8 Flash 1,068

Nearest alternatives

  • The most capable open-weights modelMiMo-V2.6-Pro$0.54 blended · Intelligence Index 46.3

Against Mercury 3. "Similar intelligence" means within 4 points or better.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Mercury 3Claude Fable 5.2
highest-scoring overall available today
GLM-5.3
just above overall
GLM-5.3 FlashX Legal
just below overall
Price per million tokens – $16.00$2.15$0.59
Tokens a second – –87–
Intelligence Index – –44.8–
Spring Prompt overall 33 883529
Rank among available models, by use case
Product listings – 8th–34th
Decks from an analysis 30th of 36 4th–27th
User surveys 21st of 27 1st–16th
Marketing planning 30th of 36 1st33rd17th
Agents and tool use pending –15th–
Professional work pending –15th–
Reasoning and knowledge – –31st–
Writing pending –24th–
Sticking to the facts pending –51st–
Speed under pressure 16th of 39 10th37th23rd

Shaded figures are better than Mercury 3's. A dash means no result.

Research and examples

In the playground: our pick in 0 of 28 tests, 80% of checks passed →

Where it has been measured

Compared with the models available today (it is not on sale itself), in the bottom quarter for decks from an analysis, user surveys and marketing planning. Results for agents and tool use, professional work, writing, and sticking to the facts are pending: those sources last updated before this model was released.

Not timed: Artificial Analysis, our source for speed, has not tested it

Every result

63 published results from 4 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 15 results
MeasureValueRankConfigurationDated
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0032 29 of 76 Mercury 3 (low reasoning)
low reasoning
19 Oct 2026
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0020 24 of 76 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 87.5% 67 of 76 Mercury 3 (low reasoning)
low reasoning
19 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 0.0% 1 of 76 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.0% 1 of 76 Mercury 3 (low reasoning)
low reasoning
19 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.0% 1 of 76 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 147
0–381
63 of 76 Mercury 3 (low reasoning)
low reasoning
19 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 491
299–659
36 of 76 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 4.2 s 73 of 76 Mercury 3 (low reasoning)
low reasoning
19 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 0.4 s 3 of 76 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Lightning 10+1: cost per gameUS dollars, lower is better $0.0010 19 of 48 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Lightning 10+1: games lost on time% of games, lower is better 0.0% 1 of 48 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Lightning 10+1: invalid moves% of moves, lower is better 0.4% 42 of 48 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better 555
263–727
23 of 48 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026
BulletBench Lightning 10+1: median move timemilliseconds, lower is better 0.4 s 3 of 48 Mercury 3 (no reasoning)
none reasoning
19 Oct 2026

Not shown: Not your cost: prices are those charged on the run date.

DeckBench · measured by Spring Prompt · 18 results
MeasureValueRankConfigurationDated
DeckBench: accurate decks% of tasks, higher is better 0.0% 32 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: caveat dropped% of tasks, lower is better 16.7% 16 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: clean layout% of tasks, higher is better 66.7% 10 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: cost per deckUS dollars, lower is better $0.0116 7 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: deck ratingrating, higher is better 726
632–814
31 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: design quality% of the maximum, higher is better 58.5% 25 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: draft figure quoted% of tasks, lower is better 33.3% 21 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: findings missing% of tasks, lower is better 16.7% 25 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: head-to-head win rate% of comparisons, higher is better 35.2% 31 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: layout defects% of tasks, lower is better 33.3% 10 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: misleading metric used% of tasks, lower is better 16.7% 31 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: output tokens per decktokens, lower is better 32,448 10 of 16 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: presentable decks% of tasks, higher is better 0.0% 17 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: recommendation late or wrong% of tasks, lower is better 83.3% 34 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: slides needing work% of tasks, lower is better 33.3% 12 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: time per deckseconds, lower is better 83.3 12 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: unsupported claims% of tasks, lower is better 16.7% 17 of 37 Mercury 3
provider default reasoning
19 Oct 2026
DeckBench: unsupported numbers% of tasks, lower is better 16.7% 28 of 37 Mercury 3
provider default reasoning
19 Oct 2026

Not shown: Not your analysis or your brand: invented companies, six public tasks, one deck per model per task at the provider's default reasoning setting.

ROASBench · measured by Spring Prompt · 9 results
MeasureValueRankConfigurationDated
ROASBench: audience scorescore out of 100, higher is better 43.2 35 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: business scorescore out of 100, higher is better 17.6 32 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: consistency scorescore out of 100, higher is better 15.1 31 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: contribution profitsimulated US dollars, higher is better $104,868 32 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: cost of a runUS dollars, lower is better $0.0533 9 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: months over budgetmonths of 12, lower is better 0 1 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: overall scorescore out of 100, higher is better 26.1 32 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: planning scorescore out of 100, higher is better 53.8 37 of 38 Mercury 3
provider default reasoning
19 Oct 2026
ROASBench: return on ad spendprofit per $1 spent, higher is better $0.10 32 of 38 Mercury 3
provider default reasoning
19 Oct 2026

Not shown: Not real ad performance: the market is a deterministic simulation of one invented skincare brand.

SurveyBench · measured by Spring Prompt · 21 results
MeasureValueRankConfigurationDated
SurveyBench: analysis ratingrating, higher is better 735
631–817
21 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: analysis scorepoints of 100, higher is better 42.2 24 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: cost per taskUS dollars, lower is better $0.0216 7 of 27 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: head-to-head win rate% of comparisons, higher is better 42.4% 18 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: leading or double-barrelled questions% of tasks, lower is better 55.6% 21 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: mistaken next steps% of tasks, lower is better 22.2% 13 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: numbers right% of answers, higher is better 63.3% 28 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: objectives unanswerable% of tasks, lower is better 0.0% 1 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: output tokens per tasktokens, lower is better 57,343 15 of 17 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: precision ignored% of tasks, lower is better 0.0% 1 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: research scorepoints of 100, higher is better 56.8 23 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: sound research% of tasks, higher is better 0.0% 17 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: stakeholder's view presumed% of tasks, lower is better 22.2% 18 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: survey plan scorepoints of 100, higher is better 90.8 18 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: survey structure% of tasks, lower is better 22.2% 12 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: time per taskseconds, lower is better 194 16 of 27 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: traps handled% of traps, higher is better 60.7% 26 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: traps missed% of tasks, lower is better 88.9% 19 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: unsupported findings% of tasks, lower is better 44.4% 11 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: wrong numbers% of tasks, lower is better 44.4% 21 of 28 Mercury 3
provider default reasoning
19 Oct 2026
SurveyBench: wrong recommendation% of tasks, lower is better 77.8% 24 of 28 Mercury 3
provider default reasoning
19 Oct 2026

Not shown: Not your customers or your data: invented organisations with simulated respondents, nine public tasks, one run per model per task at the provider's default reasoning setting.

Embed a score badge

A badge for its Spring Prompt Score and each of our benchmarks that ranked Mercury 3, from the current results. Paste the code into a page or README; it links back to where the result comes from.

Mercury 3 is #29 of 35 on the Spring Prompt Score (32 of 100, from 4 of 5 of our benchmarks), measured by Spring Prompt Spring Prompt Score · 4 of 5 benchmarks
<a href="https://springprompt.com/score#inception-mercury-3"><img src="https://springprompt.com/badge/score/inception-mercury-3.svg" alt="Mercury 3 is #29 of 35 on the Spring Prompt Score (32 of 100, from 4 of 5 of our benchmarks), measured by Spring Prompt" height="20"></a>
Mercury 3 is #30 of 36 on DeckBench (Deck rating: 726), measured by Spring Prompt DeckBench · Deck rating
<a href="https://springprompt.com/benchmarks/deckbench?focus=inception-mercury-3"><img src="https://springprompt.com/badge/deckbench/inception-mercury-3.svg" alt="Mercury 3 is #30 of 36 on DeckBench (Deck rating: 726), measured by Spring Prompt" height="20"></a>
Mercury 3 is #21 of 27 on SurveyBench (Analysis rating: 735), measured by Spring Prompt SurveyBench · Analysis rating
<a href="https://springprompt.com/benchmarks/surveybench?focus=inception-mercury-3"><img src="https://springprompt.com/badge/surveybench/inception-mercury-3.svg" alt="Mercury 3 is #21 of 27 on SurveyBench (Analysis rating: 735), measured by Spring Prompt" height="20"></a>
Mercury 3 is #30 of 36 on ROASBench (Score: 26.1), measured by Spring Prompt ROASBench · Score
<a href="https://springprompt.com/benchmarks/roasbench?focus=inception-mercury-3"><img src="https://springprompt.com/badge/roasbench/inception-mercury-3.svg" alt="Mercury 3 is #30 of 36 on ROASBench (Score: 26.1), measured by Spring Prompt" height="20"></a>
Mercury 3 is #23 of 45 on BulletBench (Lightning 10+1: 555), measured by Spring Prompt BulletBench · Lightning 10+1
<a href="https://springprompt.com/benchmarks/bulletbench?focus=inception-mercury-3"><img src="https://springprompt.com/badge/bulletbench/inception-mercury-3.svg" alt="Mercury 3 is #23 of 45 on BulletBench (Lightning 10+1: 555), measured by Spring Prompt" height="20"></a>

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.