Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Mistral Small 3.1

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 3.9× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Last verified . 23 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Mistral Small 3.1 Mistral AI

31.7

Rank #269 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Mistral Small 3.1 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4.20 (Non-Reasoning) leads 48.2 to 14.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 3.9% for Mistral Small 3.1.
  • Mistral Small 3.1 is cheaper at $0.35 / $0.56 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 128K.
  • Mistral Small 3.1 has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Mistral Small 3.1
ProviderxAIMistral AI
Noometry Index48.631.7
Released2026-02-172025-03-17
WeightsProprietaryOpen
Context window1M128K
Max output30K102K
Input $ / M tokens$1.25$0.35
Output $ / M tokens$2.50$0.56
Results tracked4628

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Mistral Small 3.1: 38.3 (#179)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
LMArena Coding14591309
LMArena WebDev1375—
WeirdML52.3%—
ALE-Bench1,150—

Agentic & Tool Use Not comparable

Grok 4.20 (Non-Reasoning): 34.4 (#46), Mistral Small 3.1: —

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
Terminal-Bench57.3%—
τ²-bench Banking18%—
LMArena Search1189—
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Mistral Small 3.1: 19.7 (#254)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
Chess Puzzles24%1%
LMArena Hard Prompts14511278
Epoch Capabilities Index151.98127.48
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Thematic Generalization63.8%—
DTBench90.1%—
LMCA38.7%—
ForecastBench61.4—

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Mistral Small 3.1: 14.7 (#301)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
OTIS Mock AIME 2024-202592.2%3.9%
LMArena Math14551262
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
Omni-MATH—24.8%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Mistral Small 3.1: 22.6 (#271)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
GPQA Diamond89.3%41.9%
LMArena Expert14391257
SimpleQA Verified30.2%—
MMLU-Pro—61%
GPQA (HELM)—39.2%

Multimodal Too close to call

Grok 4.20 (Non-Reasoning): 33.3 (#98), Mistral Small 3.1: 33.2 (#99)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
LMArena Vision12631136
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Mistral Small 3.1: 41.2 (#209)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
LMArena Non-English14411255
LMArena Chinese14811253
LMArena French14761273
LMArena German14651266
LMArena Japanese14491208
LMArena Korean14171206
LMArena Russian14581263
LMArena Spanish14431283

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Mistral Small 3.1: 63.6 (#230)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
LMArena Instruction Following14201264
IFEval—75%

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Mistral Small 3.1: 39.5 (#178)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
LMArena Longer Query14371299
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Mistral Small 3.1: 37.0 (#259)

BenchmarkGrok 4.20 (Non-Reasoning)Mistral Small 3.1
LMArena Text14511277
LMArena Creative Writing14381253
EQ-Bench Creative Writing1574761
LMArena Multi-Turn14561270
WildBench—78.8%

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Mistral Small 3.1?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 31.7 on the Noometry Index. Mistral Small 3.1 costs 3.9× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Mistral Small 3.1?

Mistral Small 3.1 is cheaper. It lists at $0.35 per million input tokens and $0.56 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

Is Grok 4.20 (Non-Reasoning) or Mistral Small 3.1 better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 38.3 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 128K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Mistral Small 3.1 share?

23 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Mistral Small 3.1 has 28.

Related comparisons

Go deeper