Noometry

Model comparison

Llama-3.3-70B-Instruct vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 30.6 on the Noometry Index.

Last verified . 15 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 1 category and Step 3 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3 leads 37.6 to 15.3.

Side by side

Llama-3.3-70B-InstructStep 3
ProviderMetaStepFun
Noometry Index30.640.5
Released2024-12-06—
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4317

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

Category by category

Coding Step 3 leads

Llama-3.3-70B-Instruct: 31.0 (#290), Step 3: 40.1 (#147)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Coding12681367
SciCode26%—
WeirdML14.4%—
BigCodeBench Instruct46.9%—
LiveBench Coding36.6%—
BigCodeBench Complete57.5%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.8 (#105), Step 3: —

BenchmarkLlama-3.3-70B-InstructStep 3
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Step 3 leads

Llama-3.3-70B-Instruct: 14.1 (#327), Step 3: 28.4 (#105)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Hard Prompts12571355
SimpleBench19.9%—
Kagi LLM Benchmark—62.3%
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
Epoch Capabilities Index127.33—
ForecastBench58.6—
LiveBench50.2%—

Math Step 3 leads

Llama-3.3-70B-Instruct: 15.3 (#298), Step 3: 37.6 (#148)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Math12671366
OTIS Mock AIME 2024-20255.1%—
LiveBench Math42.2%—
MATH Level 541.6%—

Knowledge Step 3 leads

Llama-3.3-70B-Instruct: 30.6 (#226), Step 3: 36.8 (#164)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Expert12251333
GPQA Diamond47.4%—
Confabulations22.8%—
Vectara Hallucination Rate4.1%—
MMLU86.3%—

Multimodal Not comparable

Llama-3.3-70B-Instruct: —, Step 3: 35.5 (#86)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Vision—1177

Multilingual Step 3 leads

Llama-3.3-70B-Instruct: 39.9 (#220), Step 3: 46.3 (#159)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Non-English12361327
LMArena Chinese12171397
LMArena German12511371
LMArena Korean11431269
LMArena Russian12521331
LMArena Spanish12701371
LMArena French1281—
LMArena Japanese1150—

Instruction Following Too close to call

Llama-3.3-70B-Instruct: 71.1 (#157), Step 3: 70.4 (#164)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Instruction Following12421332
LiveBench Instruction Following82.7%—

Long Context Step 3 leads

Llama-3.3-70B-Instruct: 26.4 (#295), Step 3: 40.3 (#157)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Longer Query12561326
Fiction.LiveBench33.3%—

Writing & Preference Step 3 leads

Llama-3.3-70B-Instruct: 47.6 (#207), Step 3: 54.3 (#151)

BenchmarkLlama-3.3-70B-InstructStep 3
LMArena Text12741350
LMArena Creative Writing12501321
LMArena Multi-Turn12801341
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 30.6 on the Noometry Index.

Is Llama-3.3-70B-Instruct or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 31.0 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Step 3 share?

15 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper