Model comparison

Llama 13b vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 23.9 on the Noometry Index.

Last verified . 8 shared benchmarks.

Llama 13b Meta

23.9

Rank #344 Confirmed

Step 3.5 Flash StepFun

41.7

Rank #116 Confirmed

Summary

  • They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Step 3.5 Flash in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Step 3.5 Flash leads 59.0 to 13.9.

Side by side

Llama 13b and Step 3.5 Flash specifications
Llama 13bStep 3.5 Flash
ProviderMetaStepFun
Noometry Index23.941.7
Released2023-02-242026-01-29
WeightsOpenOpen
Context window—256K
Max output—256K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.30
Results tracked2119

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

Category by category

Coding Step 3.5 Flash leads

Llama 13b: 20.9 (#332), Step 3.5 Flash: 41.7 (#106)

Coding benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Coding6831436

Reasoning Step 3.5 Flash leads

Llama 13b: 13.4 (#327), Step 3.5 Flash: 21.2 (#202)

Reasoning benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Hard Prompts7281411
NYT Connections (extended)—28.4%
BIG-Bench Hard37.9%—
Epoch Capabilities Index100.09—
HellaSwag79.2%—
LAMBADA75.2%—
PIQA80.1%—
WinoGrande73%—

Math Step 3.5 Flash leads

Llama 13b: 24.4 (#259), Step 3.5 Flash: 40.6 (#77)

Math benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Math8381408
MathArena Final-Answer Competitions—66.8%
GSM8K20.6%—

Knowledge Not comparable

Llama 13b: —, Step 3.5 Flash: 39.0 (#127)

Knowledge benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Expert—1422
ARC (AI2) Challenge52.7%—
BoolQ78.7%—
MMLU47.7%—
OpenBookQA56.4%—
TriviaQA77.9%—

Multimodal Not comparable

Llama 13b: —, Step 3.5 Flash: —

Multimodal benchmarks
BenchmarkLlama 13bStep 3.5 Flash
ScienceQA43.3%—

Multilingual Step 3.5 Flash leads

Llama 13b: 16.8 (#292), Step 3.5 Flash: 50.7 (#115)

Multilingual benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Non-English8191386
LMArena Chinese—1448
LMArena French—1421
LMArena German—1404
LMArena Japanese—1353
LMArena Korean—1350
LMArena Russian—1385
LMArena Spanish—1419

Instruction Following Step 3.5 Flash leads

Llama 13b: 36.9 (#300), Step 3.5 Flash: 73.3 (#119)

Instruction Following benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Instruction Following7811385

Long Context Not comparable

Llama 13b: —, Step 3.5 Flash: 42.8 (#112)

Long Context benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Longer Query—1402

Writing & Preference Step 3.5 Flash leads

Llama 13b: 13.9 (#307), Step 3.5 Flash: 59.0 (#108)

Writing & Preference benchmarks
BenchmarkLlama 13bStep 3.5 Flash
LMArena Text8341403
LMArena Creative Writing7941357
LMArena Multi-Turn7531405

Frequently asked questions

Is Llama 13b better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 23.9 on the Noometry Index.

Is Llama 13b or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 20.9 in the Noometry coding category.

How many benchmarks do Llama 13b and Step 3.5 Flash share?

8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper