Compare / Mercury 3 vs GLM-5.3

Mercury 3 vs GLM-5.3

Which is cheaper, which is more capable, and which does better at each kind of work, from 14 results on 2 sources that measured both models.

InceptionMercury 3 Released 19 Oct 2026 · Not on sale
Z.aiGLM-5.3 Released 14 Aug 2026 · $1.40 in · $4.40 out
Mercury 3 wins 112 too close to callGLM-5.3 wins 1

Of the 14 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? The short answer

They score about the same, so pick Mercury 3: it costs 8.0 times less per game of bullet chess on BulletBench.

  • Spring Prompt overall: Mercury 3 33, GLM-5.3 35 (out of 100; how the score works).
  • Mercury 3 is cheaper to run: $0.002 against $0.016 per game of bullet chess on BulletBench (8.0 times less).
  • Mercury 3 is newer: released 19 Oct 2026, against 14 Aug 2026 for GLM-5.3.
  • On our own benchmarks, on the results both models have: Mercury 3 does better for marketing planning and speed under pressure.

Head to head

33
Spring Prompt overall
35

Every fact side by side

Mercury 3GLM-5.3
Price per million tokensNot on sale$1.40 in · $4.40 out
Blended (3 in : 1 out)–$2.15
Cheapest host, blended–$0.40 (Wafer, FP4)
Cost per game of bullet chess (BulletBench)$0.002$0.016
Cached input, per million–$0.26 cached input
Intelligence Index–44.8
Spring Prompt overall3335
Output speed, tokens a second–87
Context window–1,048,576 tokens
Released19 Oct 2026 (newer)14 Aug 2026
WeightsClosedOpen
Developer based inthe USChina

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.

Decks from an analysisTurning a finished analysis into a deck you could present as it is 30 of 36 not measured
User surveysPlanning a user survey and reading its results without being misled 21 of 27 not measured
Marketing planningPlanning a year of ad spend without overspending 30 of 36 32 of 35
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls not measured 15 of 159
Professional workReal tasks from banking, consulting and law, business documents and freelance projects not measured 15 of 51
Reasoning and knowledgeHard questions across science, maths and general knowledge not measured 31 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality not measured 24 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 51 of 139
Speed under pressureGood decisions against a real clock (fast chess) 16 of 39 36 of 38

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.

MeasureMercury 3GLM-5.3
BulletBench measured by Spring Prompt · 3 results
Cost per game · Bullet 60sUS dollars, lower is better 24 · 44 of 62 measured $0.0020no reasoning $0.0156
Ladder Elo · Bullet 60sladder Elo, higher is better 33 · 59 of 62 measured 491no reasoning 33
Games lost on time · Bullet 60s% of games, lower is better 1 · 56 of 62 measured 0.0%no reasoning 83.3%low reasoning
ROASBench measured by Spring Prompt · 3 results
Overall scorescore out of 100, higher is better 30 · 33 of 36 measured 26.1 24.8
Audience scorescore out of 100, higher is better 33 · 29 of 36 measured 43.2 51.0
Business scorescore out of 100, higher is better 30 · 33 of 36 measured 17.6 12.9
Show all 14 results (8 more)
MeasureMercury 3GLM-5.3
BulletBench measured by Spring Prompt · 2 results
Invalid moves · Bullet 60s% of moves, lower is better 1 · 1 of 62 measured 0.0%low reasoning 0.0%
Median move time · Bullet 60smilliseconds, lower is better 3 · 42 of 62 measured 0.4 sno reasoning 1.6 slow reasoning
ROASBench measured by Spring Prompt · 6 results
Consistency scorescore out of 100, higher is better 31 · 32 of 36 measured 15.1 14.8
Contribution profitsimulated US dollars, higher is better 30 · 34 of 36 measured $104,868 $9,718
Cost of a runUS dollars, lower is better 8 · 12 of 36 measured $0.0533 $0.13
Months over budgetmonths of 12, lower is better 1 · 1 of 36 measured 0 0
Planning scorescore out of 100, higher is better 35 · 36 of 36 measured 53.8 51.7
Return on ad spendprofit per $1 spent, higher is better 30 · 34 of 36 measured $0.10 $0.01

Quick answers

Is Mercury 3 better than GLM-5.3?

They score about the same, so pick Mercury 3: it costs 8.0 times less per game of bullet chess on BulletBench.

Which is cheaper, Mercury 3 or GLM-5.3?

Mercury 3 is cheaper to run: $0.002 against $0.016 per game of bullet chess on BulletBench (8.0 times less).

Which is better for marketing planning, Mercury 3 or GLM-5.3?

Mercury 3 ranks 30 of 36 models on sale for planning a year of ad spend without overspending, against 32 for GLM-5.3.

Which is better for speed under pressure, Mercury 3 or GLM-5.3?

Mercury 3 ranks 16 of 39 models on sale for good decisions against a real clock (fast chess), against 36 for GLM-5.3.

Run Mercury 3 and GLM-5.3 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.