Noometry

Model comparison

GPT-3.5-turbo vs Phi-3.5-mini

GPT-3.5-turbo has enough public results to be ranked (#345); Phi-3.5-mini does not yet, so treat this comparison as directional.

Last verified . 4 shared benchmarks.

GPT-3.5-turbo OpenAI

23.1

Rank #345 Confirmed

Phi-3.5-mini Microsoft

36.4

Unranked Sparse

Summary

  • They share 4 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Phi-3.5-mini in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Phi-3.5-mini leads 34.0 to 23.5.
  • The biggest single-benchmark swing is BigCodeBench Complete: 50.6% for GPT-3.5-turbo and 38.5% for Phi-3.5-mini.
  • Phi-3.5-mini has downloadable open weights; the other is API-only.

Side by side

GPT-3.5-turboPhi-3.5-mini
ProviderOpenAIMicrosoft
Noometry Index23.136.4
Released2023-03-012024-08-16
WeightsProprietaryOpen
Context window16K—
Max output4K—
Input $ / M tokens$0.50—
Output $ / M tokens$1.50—
Results tracked445

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

Category by category

Coding Phi-3.5-mini leads

GPT-3.5-turbo: 23.5 (#326), Phi-3.5-mini: 34.0 (#231)

BenchmarkGPT-3.5-turboPhi-3.5-mini
BigCodeBench Instruct39.1%32.8%
BigCodeBench Complete50.6%38.5%
WeirdML3.5%—
LMArena Coding1137—
HumanEval+70.7%—
MBPP+69.7%—

Agentic & Tool Use Not comparable

GPT-3.5-turbo: —, Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
METR Time Horizons21.5%—

Reasoning Not comparable

GPT-3.5-turbo: 13.3 (#328), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
Chess Puzzles0%—
LMArena Hard Prompts1108—
Mystery Game Puzzles3%—
DTBench48.5%—
LMCA9.7%—
Adversarial NLI58.1%—
BIG-Bench Hard61.6%—
CommonsenseQA 2.057%—
Epoch Capabilities Index118.48—
ForecastBench50.4—
PIQA—81%
WinoGrande81.6%—

Math Not comparable

GPT-3.5-turbo: 6.0 (#321), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
GSM8K57.8%86.2%
FrontierMath (Tiers 1-3)0%—
OTIS Mock AIME 2024-20252.2%—
LMArena Math1142—
MATH Level 515.9%—

Knowledge Not comparable

GPT-3.5-turbo: 10.0 (#298), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
BoolQ87%78%
GPQA Diamond28%—
LMArena Expert1070—
ARC (AI2) Challenge87.4%—
MMLU71.4%—
OpenBookQA86%—
TriviaQA85.8%—

Multilingual Not comparable

GPT-3.5-turbo: 31.6 (#253), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
LMArena Non-English1108—
LMArena Chinese1075—
LMArena French1117—
LMArena German1090—
LMArena Japanese1043—
LMArena Korean1019—
LMArena Russian1123—
LMArena Spanish1120—

Instruction Following Not comparable

GPT-3.5-turbo: 58.1 (#257), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
LMArena Instruction Following1119—

Long Context Not comparable

GPT-3.5-turbo: 34.0 (#249), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
LMArena Longer Query1121—

Writing & Preference Not comparable

GPT-3.5-turbo: 25.4 (#300), Phi-3.5-mini: —

BenchmarkGPT-3.5-turboPhi-3.5-mini
LMArena Text1125—
LMArena Creative Writing1092—
EQ-Bench Creative Writing451—
LMArena Multi-Turn1117—

Frequently asked questions

Is GPT-3.5-turbo better than Phi-3.5-mini?

GPT-3.5-turbo has enough public results to be ranked (#345); Phi-3.5-mini does not yet, so treat this comparison as directional.

Is GPT-3.5-turbo or Phi-3.5-mini better for coding?

Phi-3.5-mini scores higher on coding benchmarks: 34.0 versus 23.5 in the Noometry coding category.

How many benchmarks do GPT-3.5-turbo and Phi-3.5-mini share?

4 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Phi-3.5-mini has 5.

Related comparisons

Go deeper