Compare / Mercury 3 vs GPT-6.1 Sol
Mercury 3 vs GPT-6.1 Sol
Which is cheaper, which is more capable, and which does better at each kind of work, from 47 results on 3 sources that measured both models.
Of the 47 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).
Mercury 3 or GPT-6.1 Sol? The short answer
Pick GPT-6.1 Sol if quality matters most: it scores higher (Spring Prompt overall 80 against 39). Pick Mercury 3 if cost matters more: it costs 13 times less per deck on DeckBench.
- Spring Prompt overall: Mercury 3 39, GPT-6.1 Sol 80 (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 29 Sep 2026 for GPT-6.1 Sol.
- On our own benchmarks, on the results both models have: GPT-6.1 Sol does better for decks from an analysis, user surveys and speed under pressure.
Head to head
Every fact side by side
| Mercury 3 | GPT-6.1 Sol | |
|---|---|---|
| Price per million tokens | $0.20 in · $0.70 out | $2.00 in · $10.00 out |
| Blended (3 in : 1 out) | $0.33 | $4.00 |
| Cheapest host, blended | – | $4.00 (Azure) |
| Cost per deck (DeckBench) | $0.012 | $0.15 |
| Cached input, per million | $0.020 cached input | $0.10 cached input |
| Intelligence Index | – | 51.8 |
| Spring Prompt overall | 39 | 80 |
| Output speed, tokens a second | – | 53 |
| Context window | 1,000,000 tokens | 1,050,000 tokens |
| Released | 19 Oct 2026 (newer) | 29 Sep 2026 |
| 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
- Mercury 3 first look: very fast with thinking off, too slow with it on 20 Oct 2026
- Best AI for Product Descriptions: Accuracy, Cost and Real Examples 20 Oct 2026
- AI Checkpoint: Sol’s new fast lane 9 Oct 2026
- DeepSeek-V4.1-Flash-1017 review: better at analysis, much worse at sticking to the product data 19 Oct 2026
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 | Mercury 3 | GPT-6.1 Sol |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better 7 · 25 of 32 measured | $0.0020no reasoning | $0.0210 |
| Ladder Elo · Bullet 60sladder Elo, higher is better 15 · 2 of 32 measured | 491no reasoning | 928Ultrafast (low reasoning) |
| Ladder Elo · Lightning 10+1ladder Elo, higher is better 12 · 5 of 24 measured | 555no reasoning | 584Ultrafast (low reasoning) |
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 4 · 17 of 24 measured | $0.0116 | $0.15 |
| 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. 18 · 3 of 24 measured | 812 | 1,457 |
| Accurate decks% of tasks, higher is better 20 · 1 of 24 measured | 0.0% | 100.0% |
| 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 · 3 of 13 measured | 752 | 1,473 |
| Cost per taskUS dollars, lower is better 3 · 9 of 12 measured | $0.0216 | $0.14 |
| Analysis scorepoints of 100, higher is better 12 · 1 of 13 measured | 42.2 | 96.6 |
Show all 47 results (38 more)
| Measure | Mercury 3 | GPT-6.1 Sol |
|---|---|---|
| BulletBench measured by Spring Prompt · 7 results | ||
| Cost per game · Lightning 10+1US dollars, lower is better 5 · 24 of 24 measured | $0.0010no reasoning | $0.16Ultrafast |
| Games lost on time · Bullet 60s% of games, lower is better 1 · 14 of 32 measured | 0.0%no reasoning | 25.0%Ultrafast (low reasoning) |
| Games lost on time · Lightning 10+1% of games, lower is better 1 · 17 of 24 measured | 0.0%no reasoning | 50.0%Ultrafast (low reasoning) |
| Invalid moves · Bullet 60s% of moves, lower is better 1 · 1 of 32 measured | 0.0%low reasoning | 0.0% |
| Invalid moves · Lightning 10+1% of moves, lower is better 18 · 1 of 24 measured | 0.4%no reasoning | 0.0%Ultrafast |
| Median move time · Bullet 60smilliseconds, lower is better 3 · 19 of 32 measured | 0.4 sno reasoning | 1.4 sUltrafast (low reasoning) |
| Median move time · Lightning 10+1milliseconds, lower is better 3 · 20 of 24 measured | 0.4 sno reasoning | 1.2 sUltrafast (low reasoning) |
| DeckBench measured by Spring Prompt · 14 results | ||
| Caveat dropped% of tasks, lower is better 12 · 1 of 24 measured | 16.7% | 0.0% |
| Clean layout% of tasks, higher is better 6 · 3 of 24 measured | 66.7% | 83.3% |
| Design quality% of the maximum, higher is better 16 · 8 of 24 measured | 58.5% | 71.4% |
| Draft figure quoted% of tasks, lower is better 12 · 1 of 24 measured | 33.3% | 0.0% |
| Findings missing% of tasks, lower is better 17 · 1 of 24 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. 16 · 5 of 24 measured | 44.0% | 83.6% |
| Layout defects% of tasks, lower is better 6 · 3 of 24 measured | 33.3% | 16.7% |
| Misleading metric used% of tasks, lower is better 22 · 1 of 24 measured | 16.7% | 0.0% |
| Presentable decks% of tasks, higher is better 12 · 2 of 24 measured | 0.0% | 50.0% |
| Recommendation late or wrong% of tasks, lower is better 22 · 1 of 24 measured | 83.3% | 0.0% |
| Slides needing work% of tasks, lower is better 7 · 11 of 24 measured | 33.3% | 50.0% |
| Time per deckseconds, lower is better 9 · 18 of 24 measured | 83.3 | 179 |
| Unsupported claims% of tasks, lower is better 11 · 1 of 24 measured | 16.7% | 0.0% |
| Unsupported numbers% of tasks, lower is better 20 · 1 of 24 measured | 16.7% | 0.0% |
| 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. 6 · 2 of 13 measured | 48.6% | 81.1% |
| Leading or double-barrelled questions% of tasks, lower is better 8 · 1 of 13 measured | 55.6% | 0.0% |
| Mistaken next steps% of tasks, lower is better 5 · 4 of 13 measured | 22.2% | 11.1% |
| Numbers right% of answers, higher is better 13 · 1 of 13 measured | 63.3% | 100.0% |
| Objectives unanswerable% of tasks, lower is better 1 · 1 of 13 measured | 0.0% | 0.0% |
| Precision ignored% of tasks, lower is better 1 · 1 of 13 measured | 0.0% | 0.0% |
| Research scorepoints of 100, higher is better 11 · 1 of 13 measured | 56.8 | 97.0 |
| Sound research% of tasks, higher is better 6 · 1 of 13 measured | 0.0% | 66.7% |
| Stakeholder's view presumed% of tasks, lower is better 7 · 1 of 13 measured | 22.2% | 0.0% |
| Survey plan scorepoints of 100, higher is better 6 · 1 of 13 measured | 90.8 | 97.8 |
| Survey structure% of tasks, lower is better 7 · 3 of 13 measured | 22.2% | 11.1% |
| Time per taskseconds, lower is better 10 · 11 of 12 measured | 194 | 222 |
| Traps handled% of traps, higher is better 11 · 2 of 13 measured | 60.7% | 95.7% |
| Traps missed% of tasks, lower is better 7 · 3 of 13 measured | 88.9% | 33.3% |
| Unsupported findings% of tasks, lower is better 4 · 1 of 13 measured | 44.4% | 0.0% |
| Wrong numbers% of tasks, lower is better 9 · 1 of 13 measured | 44.4% | 0.0% |
| Wrong recommendation% of tasks, lower is better 12 · 3 of 13 measured | 77.8% | 11.1% |
Compare them with other models
- 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
- GPT-6.1 Sol vs Claude Opus 5.5Most intelligent at $3–10 per million tokens
- GPT-6.1 Sol vs Muse Spark 1.3Cheapest with similar intelligence
- GPT-6.1 Sol vs GPT-6 AstraJust below overall
Quick answers
Is Mercury 3 better than GPT-6.1 Sol?
Pick GPT-6.1 Sol if quality matters most: it scores higher (Spring Prompt overall 80 against 39). Pick Mercury 3 if cost matters more: it costs 13 times less per deck on DeckBench.
Which is cheaper, Mercury 3 or GPT-6.1 Sol?
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, Mercury 3 or GPT-6.1 Sol?
GPT-6.1 Sol ranks 3 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 user surveys, Mercury 3 or GPT-6.1 Sol?
GPT-6.1 Sol ranks 3 of 13 models on sale for planning a user survey and reading its results without being misled, against 9 for Mercury 3.
Which is better for speed under pressure, Mercury 3 or GPT-6.1 Sol?
GPT-6.1 Sol ranks 3 of 27 models on sale for good decisions against a real clock (fast chess), against 10 for Mercury 3.
Which has the bigger context window, Mercury 3 or GPT-6.1 Sol?
GPT-6.1 Sol: 1,050,000 tokens, against 1,000,000 for Mercury 3.
Run Mercury 3 and GPT-6.1 Sol on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.