Noometry

Model comparison

GPT-5 Nano vs Ministral 3B

GPT-5 Nano is the stronger model overall, scoring 33.5 to 26.2 on the Noometry Index.

Last verified . 6 shared benchmarks.

GPT-5 Nano OpenAI

33.5

Rank #241 Confirmed

Ministral 3B Mistral AI

26.2

Rank #338 Confirmed

Summary

  • They share 6 benchmarks with published results for both. GPT-5 Nano scores higher in 2 categories and Ministral 3B in 1 category; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5 Nano leads 35.9 to 10.4.
  • The biggest single-benchmark swing is MATH Level 5: 95.2% for GPT-5 Nano and 14.4% for Ministral 3B.
  • Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $0.05 / $0.40 for GPT-5 Nano.
  • GPT-5 Nano accepts more context: 400K tokens versus 131K.
  • Ministral 3B has downloadable open weights; the other is API-only.

Side by side

GPT-5 NanoMinistral 3B
ProviderOpenAIMistral AI
Noometry Index33.526.2
Released2025-08-072024-10-01
WeightsProprietaryOpen
Context window400K131K
Max output128K262K
Input $ / M tokens$0.05$0.10
Output $ / M tokens$0.40$0.10
Results tracked496

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

Category by category

Coding Not comparable

GPT-5 Nano: 33.6 (#254), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
SWE-bench Verified (bash only)34.8%—
WeirdML38.1%—
LMArena Coding1351—
ALE-Bench718.67—

Agentic & Tool Use Not comparable

GPT-5 Nano: 25.8 (#106), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
Terminal-Bench21.8%—
Berkeley Function Calling Leaderboard51.5%—

Reasoning Ministral 3B leads

GPT-5 Nano: 16.3 (#306), Ministral 3B: 18.4 (#282)

BenchmarkGPT-5 NanoMinistral 3B
DTBench62.7%51.7%
LMCA7.9%5.5%
Epoch Capabilities Index139.38118.1
ARC-AGI-22.6%—
Kagi LLM Benchmark62.2%—
ARC-AGI-120.7%—
Chess Puzzles27%—
LMArena Hard Prompts1328—
Mystery Game Puzzles9%—
ForecastBench59.1—

Math GPT-5 Nano leads

GPT-5 Nano: 29.4 (#241), Ministral 3B: 26.6 (#258)

BenchmarkGPT-5 NanoMinistral 3B
MATH Level 595.2%14.4%
FrontierMath (Tiers 1-3)20%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202581.1%—
ProofBench12%—
Omni-MATH54.6%—
LMArena Math1317—
FrontierMath (Feb 2025 set)8.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5 Nano leads

GPT-5 Nano: 35.9 (#178), Ministral 3B: 10.4 (#302)

BenchmarkGPT-5 NanoMinistral 3B
GPQA Diamond69.4%25.3%
Vectara Hallucination Rate10.5%7.3%
SimpleQA Verified11.7%—
MMLU-Pro77.8%—
GPQA (HELM)67.9%—
LMArena Expert1321—

Multimodal Not comparable

GPT-5 Nano: 31.3 (#108), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
LMArena Vision1159—
VPCT37.2%—

Multilingual Not comparable

GPT-5 Nano: 45.3 (#172), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
LMArena Non-English1313—
LMArena Chinese1356—
LMArena German1327—
LMArena Japanese1226—
LMArena Korean1269—
LMArena Russian1296—
LMArena Spanish1360—

Instruction Following Not comparable

GPT-5 Nano: 75.0 (#79), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
IFEval93.2%—
LMArena Instruction Following1306—

Long Context Not comparable

GPT-5 Nano: 31.3 (#281), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
Fiction.LiveBench44.4%—
LMArena Longer Query1312—

Writing & Preference Not comparable

GPT-5 Nano: 39.1 (#249), Ministral 3B: —

BenchmarkGPT-5 NanoMinistral 3B
LMArena Text1320—
LMArena Creative Writing1249—
EQ-Bench Creative Writing705—
WildBench80.6%—
LMArena Multi-Turn1311—

Frequently asked questions

Is GPT-5 Nano better than Ministral 3B?

GPT-5 Nano is the stronger model overall, scoring 33.5 to 26.2 on the Noometry Index.

Which is cheaper, GPT-5 Nano or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; GPT-5 Nano lists at $0.05 and $0.40.

Which has the bigger context window?

GPT-5 Nano does, with 400K tokens against 131K.

How many benchmarks do GPT-5 Nano and Ministral 3B share?

6 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Ministral 3B has 6.

Related comparisons

Go deeper