Noometry

Model comparison

GPT-4 Turbo vs phi-3-medium 14B

GPT-4 Turbo and phi-3-medium 14B score almost the same on the Noometry Index (30.5 vs 29.7), so choose on price, context window or the category you care about most.

Last verified . 6 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

phi-3-medium 14B Microsoft

29.7

Rank #306 Reported

Summary

  • They share 6 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and phi-3-medium 14B in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where phi-3-medium 14B leads 27.3 to 9.0.
  • The biggest single-benchmark swing is MATH Level 5: 46.7% for GPT-4 Turbo and 17.6% for phi-3-medium 14B.
  • phi-3-medium 14B has downloadable open weights; the other is API-only.

Side by side

GPT-4 Turbophi-3-medium 14B
ProviderOpenAIMicrosoft
Noometry Index30.529.7
Released2023-11-062024-04-23
WeightsProprietaryOpen
Context window128K—
Max output4K—
Input $ / M tokens$10—
Output $ / M tokens$30—
Results tracked3613

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

Category by category

Coding phi-3-medium 14B leads

GPT-4 Turbo: 33.8 (#249), phi-3-medium 14B: 36.8 (#201)

BenchmarkGPT-4 Turbophi-3-medium 14B
BigCodeBench Instruct48.2%37.6%
BigCodeBench Complete58.2%48.7%
WeirdML18%—
LMArena Coding1268—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
METR Time Horizons36.7%—

Reasoning Not comparable

GPT-4 Turbo: 15.3 (#317), phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
Epoch Capabilities Index127.25121.23
SimpleBench25.1%—
Chess Puzzles6%—
LMArena Hard Prompts1251—
DTBench61.6%—
LMCA9.8%—
Adversarial NLI—55.8%
BIG-Bench Hard—81.4%
ForecastBench59.4—
HellaSwag—82.4%
WinoGrande—81.5%

Math phi-3-medium 14B leads

GPT-4 Turbo: 9.0 (#322), phi-3-medium 14B: 27.3 (#250)

BenchmarkGPT-4 Turbophi-3-medium 14B
MATH Level 546.7%17.6%
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
LMArena Math1272—

Knowledge GPT-4 Turbo leads

GPT-4 Turbo: 24.3 (#268), phi-3-medium 14B: 9.1 (#306)

BenchmarkGPT-4 Turbophi-3-medium 14B
GPQA Diamond46.6%27.6%
MMLU81.3%78%
Confabulations28.4%—
LMArena Expert1223—
ARC (AI2) Challenge—91.6%
OpenBookQA—87.4%
TriviaQA—73.9%

Multimodal Not comparable

GPT-4 Turbo: 30.6 (#110), phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
LMArena Vision1090—

Multilingual Not comparable

GPT-4 Turbo: 40.5 (#216), phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
LMArena Non-English1245—
LMArena Chinese1242—
LMArena French1276—
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—
LMArena Russian1259—
LMArena Spanish1260—

Instruction Following Not comparable

GPT-4 Turbo: 65.8 (#216), phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
LMArena Instruction Following1249—

Long Context Not comparable

GPT-4 Turbo: 38.0 (#206), phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
LMArena Longer Query1254—

Writing & Preference Not comparable

GPT-4 Turbo: 47.7 (#206), phi-3-medium 14B: —

BenchmarkGPT-4 Turbophi-3-medium 14B
LMArena Text1272—
LMArena Creative Writing1269—
LMArena Multi-Turn1267—

Frequently asked questions

Is GPT-4 Turbo better than phi-3-medium 14B?

GPT-4 Turbo and phi-3-medium 14B score almost the same on the Noometry Index (30.5 vs 29.7), so choose on price, context window or the category you care about most.

Is GPT-4 Turbo or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 33.8 in the Noometry coding category.

How many benchmarks do GPT-4 Turbo and phi-3-medium 14B share?

6 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and phi-3-medium 14B has 13.

Related comparisons

Go deeper