Noometry

Model comparison

GPT-4 vs Ministral 8B

GPT-4 and Ministral 8B score almost the same on the Noometry Index (29.1 vs 28.2), so choose on price, context window or the category you care about most.

Last verified . 15 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Ministral 8B Mistral AI

28.2

Rank #325 Confirmed

Summary

  • They share 15 benchmarks with published results for both. GPT-4 scores higher in 4 categories and Ministral 8B in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Ministral 8B leads 25.7 to 10.8.
  • The biggest single-benchmark swing is DTBench: 62.7% for GPT-4 and 45.7% for Ministral 8B.
  • Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $30 / $60 for GPT-4.
  • Ministral 8B accepts more context: 262K tokens versus 8K.
  • Ministral 8B has downloadable open weights; the other is API-only.

Side by side

GPT-4Ministral 8B
ProviderOpenAIMistral AI
Noometry Index29.128.2
Released2023-03-142024-10-01
WeightsProprietaryOpen
Context window8K262K
Max output8K262K
Input $ / M tokens$30$0.15
Output $ / M tokens$60$0.15
Results tracked3817

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

Category by category

Coding Ministral 8B leads

GPT-4: 31.6 (#283), Ministral 8B: 35.0 (#230)

BenchmarkGPT-4Ministral 8B
LMArena Coding12541202
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Ministral 8B: 16.4 (#148)

BenchmarkGPT-4Ministral 8B
Berkeley Function Calling Leaderboard—11.1%
METR Time Horizons36.1%—

Reasoning Too close to call

GPT-4: 17.8 (#289), Ministral 8B: 18.4 (#281)

BenchmarkGPT-4Ministral 8B
LMArena Hard Prompts12411191
DTBench62.7%45.7%
Chess Puzzles4%—
Mystery Game Puzzles12%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Ministral 8B leads

GPT-4: 10.8 (#309), Ministral 8B: 25.7 (#267)

BenchmarkGPT-4Ministral 8B
LMArena Math12691188
MATH Level 523%14.9%
OTIS Mock AIME 2024-20251.1%—
GSM8K92%—

Knowledge GPT-4 leads

GPT-4: 18.4 (#282), Ministral 8B: 12.6 (#297)

BenchmarkGPT-4Ministral 8B
GPQA Diamond35.7%27.1%
LMArena Expert12111170
Vectara Hallucination Rate—7.4%
MMLU86.4%—
TriviaQA84.8%—

Multilingual GPT-4 leads

GPT-4: 40.6 (#215), Ministral 8B: 35.1 (#247)

BenchmarkGPT-4Ministral 8B
LMArena Non-English12461165
LMArena Chinese12421193
LMArena Russian12511195
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Spanish1261—

Instruction Following GPT-4 leads

GPT-4: 65.3 (#222), Ministral 8B: 60.5 (#250)

BenchmarkGPT-4Ministral 8B
LMArena Instruction Following12411161

Long Context Too close to call

GPT-4: 37.7 (#212), Ministral 8B: 36.7 (#227)

BenchmarkGPT-4Ministral 8B
LMArena Longer Query12441212

Writing & Preference Ministral 8B leads

GPT-4: 34.9 (#268), Ministral 8B: 39.6 (#246)

BenchmarkGPT-4Ministral 8B
LMArena Text12631191
LMArena Creative Writing12441175
LMArena Multi-Turn12571166
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Ministral 8B?

GPT-4 and Ministral 8B score almost the same on the Noometry Index (29.1 vs 28.2), so choose on price, context window or the category you care about most.

Which is cheaper, GPT-4 or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Ministral 8B better for coding?

Ministral 8B scores higher on coding benchmarks: 35.0 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Ministral 8B does, with 262K tokens against 8K.

How many benchmarks do GPT-4 and Ministral 8B share?

15 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Ministral 8B has 17.

Related comparisons

Go deeper