Noometry

Model comparison

Llama-3.3-70B-Instruct vs Olmo 3.1 32b Think

Olmo 3.1 32b Think is the stronger model overall, scoring 37.3 to 30.3 on the Noometry Index.

Last verified . 15 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.3

Rank #283 Confirmed

Olmo 3.1 32b Think Allen Institute for AI (Ai2)

37.3

Rank #191 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 3 categories and Olmo 3.1 32b Think in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Olmo 3.1 32b Think leads 33.6 to 14.3.

Side by side

Llama-3.3-70B-InstructOlmo 3.1 32b Think
ProviderMetaAllen Institute for AI (Ai2)
Noometry Index30.337.3
Released2024-12-06—
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4315

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

Category by category

Coding Olmo 3.1 32b Think leads

Llama-3.3-70B-Instruct: 30.6 (#284), Olmo 3.1 32b Think: 37.1 (#186)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Coding12681292
SciCode26%—
WeirdML14.4%—
BigCodeBench Instruct46.9%—
LiveBench Coding36.6%—
BigCodeBench Complete57.5%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.6 (#100), Olmo 3.1 32b Think: —

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Olmo 3.1 32b Think leads

Llama-3.3-70B-Instruct: 13.7 (#325), Olmo 3.1 32b Think: 24.1 (#151)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Hard Prompts12571272
SimpleBench19.9%—
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
Epoch Capabilities Index127.32—
ForecastBench58.6—
LiveBench50.2%—

Math Olmo 3.1 32b Think leads

Llama-3.3-70B-Instruct: 14.3 (#292), Olmo 3.1 32b Think: 33.6 (#170)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Math12681305
OTIS Mock AIME 2024-20255.1%—
LiveBench Math42.2%—
MATH Level 541.6%—

Knowledge Olmo 3.1 32b Think leads

Llama-3.3-70B-Instruct: 30.5 (#220), Olmo 3.1 32b Think: 35.0 (#178)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Expert12251294
GPQA Diamond47.4%—
Confabulations22.8%—
Vectara Hallucination Rate4.1%—
MMLU86.3%—

Multilingual Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 40.1 (#215), Olmo 3.1 32b Think: 38.3 (#226)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Non-English12361210
LMArena Chinese12171241
LMArena French12801262
LMArena German12511260
LMArena Russian12521193
LMArena Spanish12691288
LMArena Japanese1149—
LMArena Korean1142—

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.3 (#152), Olmo 3.1 32b Think: 65.8 (#213)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Instruction Following12421246
LiveBench Instruction Following82.7%—

Long Context Olmo 3.1 32b Think leads

Llama-3.3-70B-Instruct: 26.4 (#290), Olmo 3.1 32b Think: 38.6 (#190)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Longer Query12561272
Fiction.LiveBench33.3%—

Writing & Preference Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 47.8 (#203), Olmo 3.1 32b Think: 46.4 (#215)

BenchmarkLlama-3.3-70B-InstructOlmo 3.1 32b Think
LMArena Text12741271
LMArena Creative Writing12501226
LMArena Multi-Turn12791252
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Olmo 3.1 32b Think?

Olmo 3.1 32b Think is the stronger model overall, scoring 37.3 to 30.3 on the Noometry Index.

Is Llama-3.3-70B-Instruct or Olmo 3.1 32b Think better for coding?

Olmo 3.1 32b Think scores higher on coding benchmarks: 37.1 versus 30.6 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Olmo 3.1 32b Think share?

15 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Olmo 3.1 32b Think has 15.

Related comparisons

Go deeper