Noometry

Model comparison

GPT-6 Luna vs Mistral Small 3.1

GPT-6 Luna is the stronger model overall, scoring 45.1 to 31.4 on the Noometry Index.

Last verified . 13 shared benchmarks.

GPT-6 Luna OpenAI

45.1

Rank #65 Confirmed

Mistral Small 3.1 Mistral AI

31.4

Rank #263 Confirmed

Summary

  • They share 13 benchmarks with published results for both. GPT-6 Luna scores higher in 9 categories and Mistral Small 3.1 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 35.6 to 13.7.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.35 / $0.56 for Mistral Small 3.1.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 128K.
  • Mistral Small 3.1 has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaMistral Small 3.1
ProviderOpenAIMistral AI
Noometry Index45.131.4
Released2026-09-222025-03-17
WeightsProprietaryOpen
Context window1.05M128K
Max output128K102K
Input $ / M tokens$0.10$0.35
Output $ / M tokens$0.50$0.56
Results tracked1828

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 54.7 (#24), Mistral Small 3.1: 37.7 (#175)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Coding14481309
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1583—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 31.7 (#68), Mistral Small 3.1: 18.9 (#249)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Hard Prompts14151278
NYT Connections (extended)68.7%—
Chess Puzzles—1%
Epoch Capabilities Index—127.48

Math GPT-6 Luna leads

GPT-6 Luna: 35.6 (#140), Mistral Small 3.1: 13.7 (#295)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Math13961261
OTIS Mock AIME 2024-2025—3.9%
Omni-MATH—24.8%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 40.1 (#110), Mistral Small 3.1: 22.6 (#266)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Expert14581258
GPQA Diamond—41.9%
MMLU-Pro—61%
GPQA (HELM)—39.2%

Multimodal GPT-6 Luna leads

GPT-6 Luna: 42.0 (#27), Mistral Small 3.1: 32.6 (#93)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Vision—1136
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 51.0 (#111), Mistral Small 3.1: 41.4 (#204)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Non-English13901255
LMArena Chinese14251254
LMArena Russian13921263
LMArena Spanish14161283
LMArena French—1270
LMArena German—1266
LMArena Japanese—1210
LMArena Korean—1206

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.7 (#85), Mistral Small 3.1: 63.8 (#225)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Instruction Following14141264
IFEval—75%

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.3 (#95), Mistral Small 3.1: 39.5 (#172)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Longer Query14171300

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.4 (#115), Mistral Small 3.1: 37.2 (#254)

BenchmarkGPT-6 LunaMistral Small 3.1
LMArena Text13921278
LMArena Creative Writing13571253
LMArena Multi-Turn14001270
EQ-Bench Creative Writing—761
WildBench—78.8%

Frequently asked questions

Is GPT-6 Luna better than Mistral Small 3.1?

GPT-6 Luna is the stronger model overall, scoring 45.1 to 31.4 on the Noometry Index.

Which is cheaper, GPT-6 Luna or Mistral Small 3.1?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Mistral Small 3.1 lists at $0.35 and $0.56.

Is GPT-6 Luna or Mistral Small 3.1 better for coding?

GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 37.7 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 128K.

How many benchmarks do GPT-6 Luna and Mistral Small 3.1 share?

13 benchmarks have published results for both models. GPT-6 Luna has 18 scored results on Noometry and Mistral Small 3.1 has 28.

Related comparisons

Go deeper