Noometry

Model comparison

Grok 4.6 vs Mercury 2.5

Grok 4.6 has enough public results to be ranked (#19); Mercury 2.5 does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Grok 4.6 xAI

56.8

Rank #19 Confirmed

Mercury 2.5 Inception

30.2

Unranked Sparse

Summary

  • They share 2 benchmarks with published results for both. Grok 4.6 scores higher in 1 category and Mercury 2.5 in 0 categories; one gap is clear of the uncertainty.
  • The widest gap is in math, where Grok 4.6 leads 66.8 to 22.4.
  • The biggest single-benchmark swing is ProofBench: 51% for Grok 4.6 and 3% for Mercury 2.5.
  • Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $2 / $6 for Grok 4.6.
  • Grok 4.6 accepts more context: 500K tokens versus 260K.

Side by side

Grok 4.6Mercury 2.5
ProviderxAIInception
Noometry Index56.830.2
Released2026-08-122026-09-08
WeightsProprietaryProprietary
Context window500K260K
Max output500K66K
Input $ / M tokens$2$0.04
Output $ / M tokens$6$0.15
Results tracked492

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

Category by category

Coding Not comparable

Grok 4.6: 58.0 (#14), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
ALE-Bench1,508301.65
DeepSWE67.5%—
FrontierCode48%—
CursorBench41.4%—
LMArena WebDev1620—
FrontierSWE25.3%—
SciCode56.5%—
WeirdML67.3%—
LMArena Coding1464—

Agentic & Tool Use Not comparable

Grok 4.6: 39.4 (#25), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
APEX-Agents65.3%—
GDP.pdf17.2%—
Vending-Bench 29,047—

Reasoning Not comparable

Grok 4.6: 61.3 (#18), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
ARC-AGI-267.1%—
SimpleBench75.9%—
NYT Connections (extended)80%—
ARC-AGI-187.5%—
CritPt19.7%—
Chess Puzzles40%—
EBR-Bench30.5%—
LMArena Hard Prompts1445—
Mystery Game Puzzles34%—
DTBench97.3%—
LMCA48.5%—
Epoch Capabilities Index156.48—

Math Grok 4.6 leads

Grok 4.6: 66.8 (#19), Mercury 2.5: 22.4

BenchmarkGrok 4.6Mercury 2.5
ProofBench51%3%
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 431.7%—
OTIS Mock AIME 2024-202599.2%—
LMArena Math1416—

Knowledge Not comparable

Grok 4.6: 63.3 (#18), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
GPQA Diamond94%—
SimpleQA Verified49.3%—
LMArena Expert1463—

Multimodal Not comparable

Grok 4.6: 43.9 (#18), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
LMArena Vision1265—
Blueprint-Bench 233.2%—
Furniture Assembly40%—
LMArena Document1452—

Multilingual Not comparable

Grok 4.6: 53.3 (#67), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
LMArena Non-English1422—
LMArena Chinese1479—
LMArena French1458—
LMArena German1425—
LMArena Japanese1383—
LMArena Korean1395—
LMArena Russian1427—
LMArena Spanish1408—

Instruction Following Not comparable

Grok 4.6: 75.6 (#59), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
LMArena Instruction Following1431—

Long Context Not comparable

Grok 4.6: 44.4 (#62), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
LMArena Longer Query1453—

Writing & Preference Not comparable

Grok 4.6: 62.5 (#77), Mercury 2.5: —

BenchmarkGrok 4.6Mercury 2.5
LMArena Text1427—
LMArena Creative Writing1430—
LMArena Multi-Turn1422—

Frequently asked questions

Is Grok 4.6 better than Mercury 2.5?

Grok 4.6 has enough public results to be ranked (#19); Mercury 2.5 does not yet, so treat this comparison as directional.

Which is cheaper, Grok 4.6 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 4.6 lists at $2 and $6.

Which has the bigger context window?

Grok 4.6 does, with 500K tokens against 260K.

How many benchmarks do Grok 4.6 and Mercury 2.5 share?

2 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Mercury 2.5 has 2.

Related comparisons

Go deeper