Noometry

Model comparison

Grok 4.3 vs Ministral 3B

Grok 4.3 is the stronger model overall, scoring 43.8 to 26.2 on the Noometry Index. Ministral 3B costs 16× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

Grok 4.3 xAI

43.8

Rank #86 Confirmed

Ministral 3B Mistral AI

26.2

Rank #338 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Grok 4.3 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 Grok 4.3 leads 52.5 to 10.4.
  • The biggest single-benchmark swing is GPQA Diamond: 88.8% for Grok 4.3 and 25.3% for Ministral 3B.
  • Ministral 3B is cheaper at $0.10 / $0.10 per million input/output tokens, against $1.25 / $2.50 for Grok 4.3.
  • Grok 4.3 accepts more context: 1M tokens versus 131K.
  • Ministral 3B has downloadable open weights; the other is API-only.

Side by side

Grok 4.3Ministral 3B
ProviderxAIMistral AI
Noometry Index43.826.2
Released2026-04-172024-10-01
WeightsProprietaryOpen
Context window1M131K
Max output30K262K
Input $ / M tokens$1.25$0.10
Output $ / M tokens$2.50$0.10
Results tracked406

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

Category by category

Coding Not comparable

Grok 4.3: 41.6 (#121), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
LMArena WebDev1357—
SciCode47.3%—
WeirdML49.9%—
LMArena Coding1415—
ALE-Bench944.17—

Agentic & Tool Use Not comparable

Grok 4.3: 27.7 (#99), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
GDP.pdf8%—
LMArena Search1165—
Vending-Bench 235.26—

Reasoning Grok 4.3 leads

Grok 4.3: 35.9 (#68), Ministral 3B: 18.4 (#282)

BenchmarkGrok 4.3Ministral 3B
DTBench90.7%51.7%
LMCA38.3%5.5%
Epoch Capabilities Index149.16118.1
NYT Connections (extended)55.2%—
CritPt8%—
Chess Puzzles25%—
LMArena Hard Prompts1396—
ForecastBench60.3—

Math Grok 4.3 leads

Grok 4.3: 46.0 (#74), Ministral 3B: 26.6 (#258)

BenchmarkGrok 4.3Ministral 3B
FrontierMath (Tiers 1-3)42.8%—
FrontierMath Tier 414.6%—
OTIS Mock AIME 2024-202593.3%—
ProofBench11%—
LMArena Math1388—
MATH Level 5—14.4%

Knowledge Grok 4.3 leads

Grok 4.3: 52.5 (#62), Ministral 3B: 10.4 (#302)

BenchmarkGrok 4.3Ministral 3B
GPQA Diamond88.8%25.3%
SimpleQA Verified33.2%—
Vectara Hallucination Rate—7.3%
LMArena Expert1385—

Multimodal Not comparable

Grok 4.3: 31.6 (#104), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
LMArena Vision1229—
Blueprint-Bench 20%—

Multilingual Not comparable

Grok 4.3: 50.5 (#120), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
LMArena Non-English1385—
LMArena Chinese1422—
LMArena French1412—
LMArena German1395—
LMArena Japanese1379—
LMArena Korean1356—
LMArena Russian1399—
LMArena Spanish1398—

Instruction Following Not comparable

Grok 4.3: 72.1 (#140), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
LMArena Instruction Following1366—

Long Context Not comparable

Grok 4.3: 42.5 (#123), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
LMArena Longer Query1393—

Writing & Preference Not comparable

Grok 4.3: 58.5 (#118), Ministral 3B: —

BenchmarkGrok 4.3Ministral 3B
LMArena Text1397—
LMArena Creative Writing1380—
EQ-Bench 41075—
LMArena Multi-Turn1406—

Frequently asked questions

Is Grok 4.3 better than Ministral 3B?

Grok 4.3 is the stronger model overall, scoring 43.8 to 26.2 on the Noometry Index. Ministral 3B costs 16× less per token, which makes it the better buy when Grok 4.3's lead doesn't matter for your workload.

Which is cheaper, Grok 4.3 or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.10 per million input tokens and $0.10 per million output tokens; Grok 4.3 lists at $1.25 and $2.50.

Which has the bigger context window?

Grok 4.3 does, with 1M tokens against 131K.

How many benchmarks do Grok 4.3 and Ministral 3B share?

4 benchmarks have published results for both models. Grok 4.3 has 40 scored results on Noometry and Ministral 3B has 6.

Related comparisons

Go deeper