Compare / Mercury 3 vs GLM-5.3 FlashX Legal
Mercury 3 vs GLM-5.3 FlashX Legal
Which is cheaper, which is more capable, and which does better at each kind of work, from 58 results on 4 sources that measured both models.
Of the 58 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).
Mercury 3 or GLM-5.3 FlashX Legal? The short answer
They score about the same, so pick Mercury 3: it costs 3.1 times less per deck on DeckBench.
- Spring Prompt overall: Mercury 3 33, GLM-5.3 FlashX Legal 29 (out of 100; how the score works).
- Mercury 3 is cheaper to run: $0.012 against $0.036 per deck on DeckBench (3.1 times less).
- GLM-5.3 FlashX Legal is newer: released 2 Nov 2026, against 19 Oct 2026 for Mercury 3.
- On our own benchmarks, on the results both models have: GLM-5.3 FlashX Legal does better for user surveys and marketing planning.
Head to head
Every fact side by side
| Mercury 3 | GLM-5.3 FlashX Legal | |
|---|---|---|
| Price per million tokens | Not on sale | $0.37 in · $1.25 out |
| Blended (3 in : 1 out) | – | $0.59 |
| Cheapest host, blended | – | – |
| Cost per deck (DeckBench) | $0.012 | $0.036 |
| Intelligence Index | – | – |
| Spring Prompt overall | 33 | 29 |
| Output speed, tokens a second | – | – |
| Context window | – | 1,048,576 tokens |
| Released | 19 Oct 2026 | 2 Nov 2026 (newer) |
| Weights | Closed | Closed |
| Developer based in | the US | China |
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.
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 | Mercury 3 | GLM-5.3 FlashX Legal |
|---|---|---|
| BulletBench measured by Spring Prompt · 3 results | ||
| Cost per game · Bullet 60sUS dollars, lower is better 24 · 37 of 62 measured | $0.0020no reasoning | $0.0061low reasoning |
| Ladder Elo · Bullet 60sladder Elo, higher is better 33 · 46 of 62 measured | 491no reasoning | 358low reasoning |
| Ladder Elo · Lightning 10+1ladder Elo, higher is better 23 · 38 of 45 measured | 555no reasoning | 310low reasoning |
| DeckBench measured by Spring Prompt · 3 results | ||
| Cost per deckUS dollars, lower is better 6 · 10 of 36 measured | $0.0116 | $0.0359 |
| 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. 30 · 27 of 36 measured | 726 | 809 |
| Accurate decks% of tasks, higher is better 31 · 31 of 36 measured | 0.0% | 0.0% |
| ROASBench measured by Spring Prompt · 3 results | ||
| Overall scorescore out of 100, higher is better 30 · 17 of 36 measured | 26.1 | 46.2 |
| Audience scorescore out of 100, higher is better 33 · 20 of 36 measured | 43.2 | 63.2 |
| Business scorescore out of 100, higher is better 30 · 16 of 36 measured | 17.6 | 44.9 |
| 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. 21 · 16 of 27 measured | 735 | 937 |
| Cost per taskUS dollars, lower is better 7 · 11 of 27 measured | $0.0216 | $0.0693 |
| Analysis scorepoints of 100, higher is better 24 · 23 of 27 measured | 42.2 | 53.4 |
Show all 58 results (46 more)
| Measure | Mercury 3 | GLM-5.3 FlashX Legal |
|---|---|---|
| BulletBench measured by Spring Prompt · 7 results | ||
| Cost per game · Lightning 10+1US dollars, lower is better 19 · 28 of 45 measured | $0.0010no reasoning | $0.0035low reasoning |
| Games lost on time · Bullet 60s% of games, lower is better 1 · 36 of 62 measured | 0.0%no reasoning | 37.5%low reasoning |
| Games lost on time · Lightning 10+1% of games, lower is better 1 · 37 of 45 measured | 0.0%no reasoning | 62.5%low reasoning |
| Invalid moves · Bullet 60s% of moves, lower is better 1 · 1 of 62 measured | 0.0%low reasoning | 0.0%low reasoning |
| Invalid moves · Lightning 10+1% of moves, lower is better 39 · 1 of 45 measured | 0.4%no reasoning | 0.0%low reasoning |
| Median move time · Bullet 60smilliseconds, lower is better 3 · 38 of 62 measured | 0.4 sno reasoning | 1.4 slow reasoning |
| Median move time · Lightning 10+1milliseconds, lower is better 3 · 33 of 45 measured | 0.4 sno reasoning | 0.9 slow reasoning |
| DeckBench measured by Spring Prompt · 15 results | ||
| Caveat dropped% of tasks, lower is better 16 · 36 of 36 measured | 16.7% | 50.0% |
| Clean layout% of tasks, higher is better 10 · 18 of 36 measured | 66.7% | 33.3% |
| Design quality% of the maximum, higher is better 25 · 36 of 36 measured | 58.5% | 29.3% |
| Draft figure quoted% of tasks, lower is better 21 · 36 of 36 measured | 33.3% | 83.3% |
| Findings missing% of tasks, lower is better 25 · 36 of 36 measured | 16.7% | 50.0% |
| 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. 30 · 23 of 36 measured | 35.2% | 44.6% |
| Layout defects% of tasks, lower is better 10 · 18 of 36 measured | 33.3% | 66.7% |
| Misleading metric used% of tasks, lower is better 31 · 36 of 36 measured | 16.7% | 50.0% |
| Output tokens per decktokens, lower is better 10 · 8 of 15 measured | 32,448 | 27,796 |
| Presentable decks% of tasks, higher is better 17 · 17 of 36 measured | 0.0% | 0.0% |
| Recommendation late or wrong% of tasks, lower is better 33 · 33 of 36 measured | 83.3% | 83.3% |
| Slides needing work% of tasks, lower is better 12 · 26 of 36 measured | 33.3% | 66.7% |
| Time per deckseconds, lower is better 12 · 23 of 36 measured | 83.3 | 175 |
| Unsupported claims% of tasks, lower is better 17 · 35 of 36 measured | 16.7% | 66.7% |
| Unsupported numbers% of tasks, lower is better 28 · 35 of 36 measured | 16.7% | 50.0% |
| ROASBench measured by Spring Prompt · 6 results | ||
| Consistency scorescore out of 100, higher is better 31 · 19 of 36 measured | 15.1 | 29.0 |
| Contribution profitsimulated US dollars, higher is better 30 · 12 of 36 measured | $104,868 | $695,680 |
| Cost of a runUS dollars, lower is better 8 · 14 of 36 measured | $0.0533 | $0.16 |
| Months over budgetmonths of 12, lower is better 1 · 33 of 36 measured | 0 | 1 |
| Planning scorescore out of 100, higher is better 35 · 14 of 36 measured | 53.8 | 54.9 |
| Return on ad spendprofit per $1 spent, higher is better 30 · 15 of 36 measured | $0.10 | $0.55 |
| 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. 18 · 9 of 27 measured | 42.4% | 57.8% |
| Leading or double-barrelled questions% of tasks, lower is better 21 · 15 of 27 measured | 55.6% | 44.4% |
| Mistaken next steps% of tasks, lower is better 13 · 20 of 27 measured | 22.2% | 44.4% |
| Numbers right% of answers, higher is better 27 · 23 of 27 measured | 63.3% | 94.9% |
| Objectives unanswerable% of tasks, lower is better 1 · 24 of 27 measured | 0.0% | 22.2% |
| Output tokens per tasktokens, lower is better 15 · 14 of 17 measured | 57,343 | 51,553 |
| Precision ignored% of tasks, lower is better 1 · 19 of 27 measured | 0.0% | 22.2% |
| Research scorepoints of 100, higher is better 23 · 22 of 27 measured | 56.8 | 59.2 |
| Sound research% of tasks, higher is better 17 · 13 of 27 measured | 0.0% | 11.1% |
| Stakeholder's view presumed% of tasks, lower is better 18 · 18 of 27 measured | 22.2% | 22.2% |
| Survey plan scorepoints of 100, higher is better 18 · 25 of 27 measured | 90.8 | 72.7 |
| Survey structure% of tasks, lower is better 12 · 25 of 27 measured | 22.2% | 44.4% |
| Time per taskseconds, lower is better 16 · 23 of 27 measured | 194 | 435 |
| Traps handled% of traps, higher is better 25 · 19 of 27 measured | 60.7% | 83.0% |
| Traps missed% of tasks, lower is better 19 · 15 of 27 measured | 88.9% | 66.7% |
| Unsupported findings% of tasks, lower is better 11 · 16 of 27 measured | 44.4% | 77.8% |
| Wrong numbers% of tasks, lower is better 21 · 19 of 27 measured | 44.4% | 33.3% |
| Wrong recommendation% of tasks, lower is better 24 · 23 of 27 measured | 77.8% | 55.6% |
Compare them with other models
Quick answers
Is Mercury 3 better than GLM-5.3 FlashX Legal?
They score about the same, so pick Mercury 3: it costs 3.1 times less per deck on DeckBench.
Which is cheaper, Mercury 3 or GLM-5.3 FlashX Legal?
Mercury 3 is cheaper to run: $0.012 against $0.036 per deck on DeckBench (3.1 times less).
Which is better for decks from an analysis, Mercury 3 or GLM-5.3 FlashX Legal?
GLM-5.3 FlashX Legal ranks 27 of 36 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, Mercury 3 or GLM-5.3 FlashX Legal?
GLM-5.3 FlashX Legal ranks 16 of 27 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, Mercury 3 or GLM-5.3 FlashX Legal?
GLM-5.3 FlashX Legal ranks 17 of 36 models on sale for planning a year of ad spend without overspending, against 30 for Mercury 3.
Which is better for speed under pressure, Mercury 3 or GLM-5.3 FlashX Legal?
Mercury 3 ranks 16 of 39 models on sale for good decisions against a real clock (fast chess), against 22 for GLM-5.3 FlashX Legal.
Run Mercury 3 and GLM-5.3 FlashX Legal 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.