Noometry

Model comparison

Olmo 2 0325 32b Instruct vs Phi 3 Small 8k Instruct

Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 29.3 on the Noometry Index.

Last verified . 11 shared benchmarks.

Olmo 2 0325 32b Instruct Allen Institute for AI (Ai2)

32.7

Rank #254 Confirmed

Phi 3 Small 8k Instruct Microsoft

29.3

Rank #314 Confirmed

Summary

  • They share 11 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 6 categories and Phi 3 Small 8k Instruct in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Olmo 2 0325 32b Instruct leads 42.1 to 31.1.

Side by side

Olmo 2 0325 32b InstructPhi 3 Small 8k Instruct
ProviderAllen Institute for AI (Ai2)Microsoft
Noometry Index32.729.3
Released—2024-04-23
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1632

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

Category by category

Coding Olmo 2 0325 32b Instruct leads

Olmo 2 0325 32b Instruct: 35.2 (#227), Phi 3 Small 8k Instruct: 27.9 (#318)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Coding12101101
LiveBench Coding—20.3%

Reasoning Olmo 2 0325 32b Instruct leads

Olmo 2 0325 32b Instruct: 23.6 (#175), Phi 3 Small 8k Instruct: 14.8 (#323)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Hard Prompts12081100
LiveBench Reasoning—15.9%
LiveBench Data Analysis—30.3%
Adversarial NLI—58.1%
BIG-Bench Hard—79.1%
HellaSwag—77%
LiveBench—24%
WinoGrande—81.5%

Math Too close to call

Olmo 2 0325 32b Instruct: 26.8 (#255), Phi 3 Small 8k Instruct: 27.6 (#248)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Math12081151
Omni-MATH16.1%—
LiveBench Math—17.6%

Knowledge Phi 3 Small 8k Instruct leads

Olmo 2 0325 32b Instruct: 19.5 (#279), Phi 3 Small 8k Instruct: 29.1 (#240)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
MMLU-Pro41.4%—
GPQA (HELM)28.7%—
LMArena Expert—1067
ARC (AI2) Challenge—90.7%
MMLU—75.7%
OpenBookQA—88%
TriviaQA—58.1%

Multilingual Olmo 2 0325 32b Instruct leads

Olmo 2 0325 32b Instruct: 34.8 (#248), Phi 3 Small 8k Instruct: 28.5 (#272)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Non-English11601058
LMArena Chinese11921061
LMArena Russian11871111
LMArena French—1135
LMArena German—1080
LMArena Japanese—966
LMArena Korean—894
LMArena Spanish—1111

Instruction Following Olmo 2 0325 32b Instruct leads

Olmo 2 0325 32b Instruct: 61.5 (#244), Phi 3 Small 8k Instruct: 51.9 (#292)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Instruction Following11861087
LiveBench Instruction Following—47.2%
IFEval78%—

Long Context Olmo 2 0325 32b Instruct leads

Olmo 2 0325 32b Instruct: 36.2 (#234), Phi 3 Small 8k Instruct: 33.0 (#267)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Longer Query11941088

Writing & Preference Olmo 2 0325 32b Instruct leads

Olmo 2 0325 32b Instruct: 42.1 (#236), Phi 3 Small 8k Instruct: 31.1 (#284)

BenchmarkOlmo 2 0325 32b InstructPhi 3 Small 8k Instruct
LMArena Text12181110
LMArena Creative Writing11991083
LMArena Multi-Turn12211068
WildBench73.4%—
LiveBench Language—12.9%

Frequently asked questions

Is Olmo 2 0325 32b Instruct better than Phi 3 Small 8k Instruct?

Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.7 to 29.3 on the Noometry Index.

Is Olmo 2 0325 32b Instruct or Phi 3 Small 8k Instruct better for coding?

Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 35.2 versus 27.9 in the Noometry coding category.

How many benchmarks do Olmo 2 0325 32b Instruct and Phi 3 Small 8k Instruct share?

11 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Phi 3 Small 8k Instruct has 32.

Related comparisons

Go deeper