Noometry

Model comparison

Olmo 3.1 32b Instruct vs Phi 3 Mini 4k Instruct

Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 27.4 on the Noometry Index.

Last verified . 16 shared benchmarks.

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

38.8

Rank #168 Confirmed

Phi 3 Mini 4k Instruct Microsoft

27.4

Rank #324 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Olmo 3.1 32b Instruct scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Olmo 3.1 32b Instruct leads 50.4 to 27.7.

Side by side

Olmo 3.1 32b InstructPhi 3 Mini 4k Instruct
ProviderAllen Institute for AI (Ai2)Microsoft
Noometry Index38.827.4
Released—2024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1635

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

Category by category

Coding Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 38.9 (#154), Phi 3 Mini 4k Instruct: 26.1 (#319)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Coding13461093
LiveBench Coding—15.5%
HumanEval+—59.1%
MBPP+—54.2%

Reasoning Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 25.4 (#131), Phi 3 Mini 4k Instruct: 13.6 (#326)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Hard Prompts13221072
Chess Puzzles—0%
LiveBench Reasoning—26.8%
LiveBench Data Analysis—34.7%
Adversarial NLI—52.8%
BIG-Bench Hard—71.7%
HellaSwag—76.7%
LiveBench—22.4%
WinoGrande—70.8%

Math Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 33.6 (#169), Phi 3 Mini 4k Instruct: 24.5 (#258)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Math13051111
LiveBench Math—15.7%

Knowledge Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 35.4 (#175), Phi 3 Mini 4k Instruct: 27.9 (#241)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Expert13071045
ARC (AI2) Challenge—84.9%
MMLU—68.8%
OpenBookQA—88%
TriviaQA—64%

Multilingual Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 42.8 (#185), Phi 3 Mini 4k Instruct: 26.5 (#275)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Non-English12751021
LMArena Chinese13041021
LMArena French13281075
LMArena German12831044
LMArena Korean1206905
LMArena Russian12681022
LMArena Spanish13371084
LMArena Japanese—935

Instruction Following Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 68.8 (#182), Phi 3 Mini 4k Instruct: 48.0 (#298)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Instruction Following12981053
LiveBench Instruction Following—39.1%

Long Context Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 39.9 (#161), Phi 3 Mini 4k Instruct: 31.7 (#271)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Longer Query13121044

Writing & Preference Olmo 3.1 32b Instruct leads

Olmo 3.1 32b Instruct: 50.4 (#179), Phi 3 Mini 4k Instruct: 27.7 (#295)

BenchmarkOlmo 3.1 32b InstructPhi 3 Mini 4k Instruct
LMArena Text13111073
LMArena Creative Writing12641037
LMArena Multi-Turn13091018
LiveBench Language—9.2%

Frequently asked questions

Is Olmo 3.1 32b Instruct better than Phi 3 Mini 4k Instruct?

Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 27.4 on the Noometry Index.

Is Olmo 3.1 32b Instruct or Phi 3 Mini 4k Instruct better for coding?

Olmo 3.1 32b Instruct scores higher on coding benchmarks: 38.9 versus 26.1 in the Noometry coding category.

How many benchmarks do Olmo 3.1 32b Instruct and Phi 3 Mini 4k Instruct share?

16 benchmarks have published results for both models. Olmo 3.1 32b Instruct has 16 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.

Related comparisons

Go deeper