Noometry

Model comparison

GPT-6 Luna vs Mistral Medium 3.5

GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.2 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Mistral Medium 3.5 Mistral AI

40.2

Rank #152 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-6 Luna scores higher in 5 categories and Mistral Medium 3.5 in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 39.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 68.7% for GPT-6 Luna and 12.9% for Mistral Medium 3.5.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 262K.
  • Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaMistral Medium 3.5
ProviderOpenAIMistral AI
Noometry Index53.340.2
Released2026-09-22—
WeightsProprietaryOpen
Context window1.05M262K
Max output128K210K
Input $ / M tokens$0.10$1.50
Output $ / M tokens$0.50$7.50
Results tracked4222

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 55.5 (#25), Mistral Medium 3.5: 36.0 (#213)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena WebDev15811264
LMArena Coding14391461
DeepSWE66.6%—
FrontierCode42.4%—
SciCode54.6%—
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Mistral Medium 3.5: —

BenchmarkGPT-6 LunaMistral Medium 3.5
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Mistral Medium 3.5: 17.3 (#295)

BenchmarkGPT-6 LunaMistral Medium 3.5
NYT Connections (extended)68.7%12.9%
LMArena Hard Prompts14111436
Epoch Capabilities Index156.28141.35
ARC-AGI-259.3%—
Kagi LLM Benchmark—41.4%
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Mistral Medium 3.5: 39.1 (#113)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Math14161431
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
OTIS Mock AIME 2024-202598.9%—
ProofBench64%—

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Mistral Medium 3.5: 40.0 (#126)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Expert14441432
GPQA Diamond90.5%—
SimpleQA Verified41.4%—

Multimodal GPT-6 Luna leads

GPT-6 Luna: 42.4 (#30), Mistral Medium 3.5: 38.3 (#65)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Vision12171223
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual Mistral Medium 3.5 leads

GPT-6 Luna: 50.5 (#117), Mistral Medium 3.5: 51.9 (#100)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Non-English13861404
LMArena Chinese14331442
LMArena French14201448
LMArena German13691451
LMArena Korean13601385
LMArena Russian13941395
LMArena Spanish13931409
LMArena Japanese1369—

Instruction Following Too close to call

GPT-6 Luna: 74.3 (#99), Mistral Medium 3.5: 74.6 (#90)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Instruction Following14091415

Long Context Too close to call

GPT-6 Luna: 43.0 (#111), Mistral Medium 3.5: 43.2 (#103)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Longer Query14091415

Writing & Preference Too close to call

GPT-6 Luna: 58.3 (#119), Mistral Medium 3.5: 58.5 (#117)

BenchmarkGPT-6 LunaMistral Medium 3.5
LMArena Text13911421
LMArena Creative Writing13631374
LMArena Multi-Turn13961423
EQ-Bench 4—993

Frequently asked questions

Is GPT-6 Luna better than Mistral Medium 3.5?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 40.2 on the Noometry Index.

Which is cheaper, GPT-6 Luna or Mistral Medium 3.5?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is GPT-6 Luna or Mistral Medium 3.5 better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 36.0 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 262K.

How many benchmarks do GPT-6 Luna and Mistral Medium 3.5 share?

20 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Mistral Medium 3.5 has 22.

Related comparisons

Go deeper