Noometry

Model comparison

Llama-3.3-70B-Instruct vs Olmo 3 32b Think

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 30.6 on the Noometry Index.

Last verified . 14 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Olmo 3 32b Think Allen Institute for AI (Ai2)

38.7

Rank #183 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 1 category and Olmo 3 32b Think in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Olmo 3 32b Think leads 36.5 to 15.3.

Side by side

Llama-3.3-70B-InstructOlmo 3 32b Think
ProviderMetaAllen Institute for AI (Ai2)
Noometry Index30.638.7
Released2024-12-06—
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4314

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

Category by category

Coding Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 31.0 (#290), Olmo 3 32b Think: 38.6 (#172)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Coding12681319
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), Olmo 3 32b Think: —

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 14.1 (#327), Olmo 3 32b Think: 25.9 (#140)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Hard Prompts12571302
SimpleBench19.9%—
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
Epoch Capabilities Index127.33—
ForecastBench58.6—
LiveBench50.2%—

Math Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 15.3 (#298), Olmo 3 32b Think: 36.5 (#165)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Math12671316
OTIS Mock AIME 2024-20255.1%—
LiveBench Math42.2%—
MATH Level 541.6%—

Knowledge Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 30.6 (#226), Olmo 3 32b Think: 35.0 (#190)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Expert12251273
GPQA Diamond47.4%—
Confabulations22.8%—
Vectara Hallucination Rate4.1%—
MMLU86.3%—

Multilingual Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 39.9 (#220), Olmo 3 32b Think: 41.2 (#210)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Non-English12361255
LMArena Chinese12171300
LMArena French12811291
LMArena German12511290
LMArena Russian12521254
LMArena Japanese1150—
LMArena Korean1143—
LMArena Spanish1270—

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.1 (#157), Olmo 3 32b Think: 67.2 (#198)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Instruction Following12421275
LiveBench Instruction Following82.7%—

Long Context Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 26.4 (#295), Olmo 3 32b Think: 39.4 (#182)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Longer Query12561296
Fiction.LiveBench33.3%—

Writing & Preference Olmo 3 32b Think leads

Llama-3.3-70B-Instruct: 47.6 (#207), Olmo 3 32b Think: 49.1 (#193)

BenchmarkLlama-3.3-70B-InstructOlmo 3 32b Think
LMArena Text12741300
LMArena Creative Writing12501256
LMArena Multi-Turn12801290
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Olmo 3 32b Think?

Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 30.6 on the Noometry Index.

Is Llama-3.3-70B-Instruct or Olmo 3 32b Think better for coding?

Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 31.0 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Olmo 3 32b Think share?

14 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Olmo 3 32b Think has 14.

Related comparisons

Go deeper