Noometry

Model comparison

Grok 4.20 Multi-Agent vs Mercury 2.5

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 33.5 on the Noometry Index. Mercury 2.5 costs 23× less per token, which makes it the better buy when Grok 4.20 Multi-Agent's lead doesn't matter for your workload.

Last verified . 0 shared benchmarks.

Grok 4.20 Multi-Agent xAI

46.2

Rank #65 Confirmed

Mercury 2.5 Inception

33.5

Rank #242 Reported

Summary

  • The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 22.4.
  • Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
  • Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 260K.

Side by side

Grok 4.20 Multi-AgentMercury 2.5
ProviderxAIInception
Noometry Index46.233.5
Released2026-03-092026-09-08
WeightsProprietaryProprietary
Context window1M260K
Max output30K66K
Input $ / M tokens$1.25$0.04
Output $ / M tokens$2.50$0.15
Results tracked204

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.0 (#92), Mercury 2.5: 39.5 (#156)

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
SciCode—38.5%
LMArena Coding1457—
ALE-Bench—301.65

Agentic & Tool Use Not comparable

Grok 4.20 Multi-Agent: —, Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Search1204—

Reasoning Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 43.9 (#48), Mercury 2.5: 22.4 (#193)

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
NYT Connections (extended)89.6%—
CritPt—0%
LMArena Hard Prompts1448—

Math Grok 4.20 Multi-Agent leads

Grok 4.20 Multi-Agent: 39.4 (#104), Mercury 2.5: 23.3 (#272)

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
ProofBench—3%
LMArena Math1442—

Knowledge Not comparable

Grok 4.20 Multi-Agent: 40.4 (#119), Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Expert1445—

Multimodal Not comparable

Grok 4.20 Multi-Agent: 40.5 (#48), Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Vision1259—

Multilingual Not comparable

Grok 4.20 Multi-Agent: 54.4 (#43), Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Non-English1440—
LMArena Chinese1475—
LMArena French1466—
LMArena German1456—
LMArena Japanese1405—
LMArena Korean1416—
LMArena Russian1457—
LMArena Spanish1447—

Instruction Following Not comparable

Grok 4.20 Multi-Agent: 74.8 (#84), Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Instruction Following1420—

Long Context Not comparable

Grok 4.20 Multi-Agent: 43.7 (#88), Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Longer Query1431—

Writing & Preference Not comparable

Grok 4.20 Multi-Agent: 64.0 (#59), Mercury 2.5: —

BenchmarkGrok 4.20 Multi-AgentMercury 2.5
LMArena Text1450—
LMArena Creative Writing1436—
LMArena Multi-Turn1452—

Frequently asked questions

Is Grok 4.20 Multi-Agent better than Mercury 2.5?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 33.5 on the Noometry Index. Mercury 2.5 costs 23× less per token, which makes it the better buy when Grok 4.20 Multi-Agent's lead doesn't matter for your workload.

Which is cheaper, Grok 4.20 Multi-Agent or Mercury 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.

Is Grok 4.20 Multi-Agent or Mercury 2.5 better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 39.5 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 Multi-Agent does, with 1M tokens against 260K.

How many benchmarks do Grok 4.20 Multi-Agent and Mercury 2.5 share?

0 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Mercury 2.5 has 4.

Related comparisons

Go deeper