Noometry

Model comparison

GPT-5.4 mini vs Ministral 3B

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 25.6 on the Noometry Index. Ministral 3B costs 42× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

Last verified . 5 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

Ministral 3B Mistral AI

25.6

Rank #336 Confirmed

Summary

  • They share 5 benchmarks with published results for both. GPT-5.4 mini scores higher in 3 categories and Ministral 3B in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.4 to 10.4.
  • The biggest single-benchmark swing is GPQA Diamond: 86.9% for GPT-5.4 mini and 25.3% for Ministral 3B.
  • Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
  • GPT-5.4 mini accepts more context: 400K tokens versus 128K.
  • Ministral 3B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniMinistral 3B
ProviderOpenAIMistral AI
Noometry Index44.825.6
Released2026-03-172024-10-01
WeightsProprietaryOpen
Context window400K128K
Max output128K128K
Input $ / M tokens$0.75$0.04
Output $ / M tokens$4.50$0.04
Results tracked466

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

Category by category

Coding Not comparable

GPT-5.4 mini: 45.0 (#67), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
LMArena Coding1438—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.6 (#74), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), Ministral 3B: 17.7 (#278)

BenchmarkGPT-5.4 miniMinistral 3B
DTBench80%51.7%
LMCA40.8%5.5%
Epoch Capabilities Index148.83118.08
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
Thematic Generalization61.7%—
LMArena Hard Prompts1424—
Mystery Game Puzzles11%—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.4 (#63), Ministral 3B: 24.5 (#257)

BenchmarkGPT-5.4 miniMinistral 3B
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
LMArena Math1418—
MATH Level 5—14.4%
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.4 (#62), Ministral 3B: 10.4 (#297)

BenchmarkGPT-5.4 miniMinistral 3B
GPQA Diamond86.9%25.3%
Vectara Hallucination Rate5.5%7.3%
SimpleQA Verified29.4%—
LMArena Expert1434—

Multimodal Not comparable

GPT-5.4 mini: 39.0 (#51), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
LMArena Vision1245—

Multilingual Not comparable

GPT-5.4 mini: 52.1 (#94), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
LMArena Non-English1405—
LMArena Chinese1446—
LMArena French1440—
LMArena German1407—
LMArena Japanese1375—
LMArena Korean1369—
LMArena Russian1417—
LMArena Spanish1403—

Instruction Following Not comparable

GPT-5.4 mini: 74.3 (#99), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
LMArena Instruction Following1405—

Long Context Not comparable

GPT-5.4 mini: 42.9 (#107), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
LMArena Longer Query1407—

Writing & Preference Not comparable

GPT-5.4 mini: 64.2 (#56), Ministral 3B: —

BenchmarkGPT-5.4 miniMinistral 3B
LMArena Text1411—
LMArena Creative Writing1370—
EQ-Bench Creative Writing1665—
LMArena Multi-Turn1429—

Frequently asked questions

Is GPT-5.4 mini better than Ministral 3B?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 25.6 on the Noometry Index. Ministral 3B costs 42× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

Which is cheaper, GPT-5.4 mini or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 128K.

How many benchmarks do GPT-5.4 mini and Ministral 3B share?

5 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Ministral 3B has 6.

Related comparisons

Go deeper