Model comparison

Mercury 2 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 39.1 on the Noometry Index. Mercury 2 costs 3.8× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 14 shared benchmarks.

Mercury 2 Inception

39.1

Rank #175 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Mercury 2 scores higher in 0 categories and Step 5 Preview in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Step 5 Preview leads 51.8 to 33.5.
  • The biggest single-benchmark swing is SciCode: 38.7% for Mercury 2 and 58.9% for Step 5 Preview.
  • Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 128K.

Side by side

Mercury 2 and Step 5 Preview specifications
Mercury 2Step 5 Preview
ProviderInceptionStepFun
Noometry Index39.147.9
Released2026-02-202026-09-16
WeightsProprietaryProprietary
Context window128K1.02M
Max output50K66K
Input $ / M tokens$0.25$1
Output $ / M tokens$0.75$2.70
Results tracked1718

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

Category by category

Coding Step 5 Preview leads

Mercury 2: 33.5 (#255), Step 5 Preview: 51.8 (#36)

Coding benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena WebDev11711564
SciCode38.7%58.9%
LMArena Coding13911480
WeirdML43.2%—
ALE-Bench785.58—

Reasoning Step 5 Preview leads

Mercury 2: 23.8 (#170), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
BenchmarkMercury 2Step 5 Preview
CritPt0.8%20.9%
LMArena Hard Prompts13621465

Math Not comparable

Mercury 2: —, Step 5 Preview: 46.1 (#72)

Math benchmarks
BenchmarkMercury 2Step 5 Preview
ProofBench—42%
LMArena Math—1470

Knowledge Step 5 Preview leads

Mercury 2: 36.2 (#172), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena Expert13581470
Vectara Hallucination Rate12.3%—

Multimodal Not comparable

Mercury 2: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

Mercury 2: 46.6 (#157), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena Non-English13311432
LMArena Chinese14171519
LMArena Russian13041436
LMArena Spanish—1439

Instruction Following Step 5 Preview leads

Mercury 2: 70.2 (#165), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena Instruction Following13291444

Long Context Step 5 Preview leads

Mercury 2: 40.5 (#154), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena Longer Query13301455

Writing & Preference Step 5 Preview leads

Mercury 2: 53.8 (#155), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
BenchmarkMercury 2Step 5 Preview
LMArena Text13551442
LMArena Creative Writing12891410
LMArena Multi-Turn13581447

Frequently asked questions

Is Mercury 2 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 39.1 on the Noometry Index. Mercury 2 costs 3.8× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, Mercury 2 or Step 5 Preview?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Mercury 2 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 128K.

How many benchmarks do Mercury 2 and Step 5 Preview share?

14 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper