Model comparison

Gemini 1.5 Flash (May 2024) vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 43.8 to 32.9 on the Noometry Index.

Last verified . 0 shared benchmarks.

Gemini 1.5 Flash (May 2024) Google

32.9

Rank #240 Confirmed

Step 5 Preview StepFun

43.8

Rank #78 Reported

Summary

  • The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 20.8.

Side by side

Gemini 1.5 Flash (May 2024) and Step 5 Preview specifications
Gemini 1.5 Flash (May 2024)Step 5 Preview
ProviderGoogleStepFun
Noometry Index32.943.8
Released2024-05-142026-09-16
WeightsProprietaryProprietary
Context window—1.02M
Max output—66K
Input $ / M tokens—$1
Output $ / M tokens—$2.70
Results tracked423

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

Category by category

Coding Step 5 Preview leads

Gemini 1.5 Flash (May 2024): 33.9 (#233), Step 5 Preview: 50.6 (#40)

Coding benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
LMArena WebDev—1569
SciCode—58.9%
WeirdML24.9%—
BigCodeBench Instruct43.5%—
LMArena Coding1262—
BigCodeBench Complete55.1%—
HumanEval+75.6%—
MBPP+67.5%—

Agentic & Tool Use Not comparable

Gemini 1.5 Flash (May 2024): 26.3 (#97), Step 5 Preview: —

Agentic & Tool Use benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
BALROG14.6%—

Reasoning Step 5 Preview leads

Gemini 1.5 Flash (May 2024): 20.8 (#212), Step 5 Preview: 38.0 (#58)

Reasoning benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
CritPt—20.9%
LMArena Hard Prompts1257—
DTBench53.8%—
Epoch Capabilities Index129.37—
ForecastBench53.9—
PIQA87.5%—

Math Not comparable

Gemini 1.5 Flash (May 2024): 20.8 (#274), Step 5 Preview: —

Math benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
OTIS Mock AIME 2024-202516.3%—
Omni-MATH30.4%—
LMArena Math1269—
MATH Level 561.9%—
FrontierMath (Feb 2025 set)0%—
GSM8K82.4%—

Knowledge Not comparable

Gemini 1.5 Flash (May 2024): 26.2 (#253), Step 5 Preview: —

Knowledge benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
GPQA Diamond47.3%—
MMLU-Pro67.8%—
GPQA (HELM)43.7%—
LMArena Expert1233—
BoolQ85.8%—
MMLU77.9%—

Multimodal Not comparable

Gemini 1.5 Flash (May 2024): 35.3 (#76), Step 5 Preview: —

Multimodal benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
LMArena Vision1141—
Video-MME70.3%—
GeoBench76%—

Multilingual Not comparable

Gemini 1.5 Flash (May 2024): 43.1 (#184), Step 5 Preview: —

Multilingual benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
LMArena Non-English1278—
LMArena Chinese1295—
LMArena French1257—
LMArena German1262—
LMArena Japanese1252—
LMArena Korean1220—
LMArena Russian1288—
LMArena Spanish1242—

Instruction Following Not comparable

Gemini 1.5 Flash (May 2024): 67.0 (#199), Step 5 Preview: —

Instruction Following benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
IFEval83.1%—
LMArena Instruction Following1258—

Long Context Not comparable

Gemini 1.5 Flash (May 2024): 39.0 (#182), Step 5 Preview: —

Long Context benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
LMArena Longer Query1284—

Writing & Preference Not comparable

Gemini 1.5 Flash (May 2024): 48.9 (#190), Step 5 Preview: —

Writing & Preference benchmarks
BenchmarkGemini 1.5 Flash (May 2024)Step 5 Preview
LMArena Text1287—
LMArena Creative Writing1285—
WildBench79.2%—
LMArena Multi-Turn1253—

Frequently asked questions

Is Gemini 1.5 Flash (May 2024) better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 32.9 on the Noometry Index.

Is Gemini 1.5 Flash (May 2024) or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 33.9 in the Noometry coding category.

How many benchmarks do Gemini 1.5 Flash (May 2024) and Step 5 Preview share?

0 benchmarks have published results for both models. Gemini 1.5 Flash (May 2024) has 42 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper