Noometry

Model comparison

GPT-6 Luna vs Granite 3.1 8b Instruct

GPT-6 Luna is the stronger model overall, scoring 53.3 to 32.4 on the Noometry Index.

Last verified . 12 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Granite 3.1 8b Instruct IBM

32.4

Rank #258 Confirmed

Summary

  • They share 12 benchmarks with published results for both. GPT-6 Luna scores higher in 9 categories and Granite 3.1 8b Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 33.0.
  • Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaGranite 3.1 8b Instruct
ProviderOpenAIIBM
Noometry Index53.332.4
Released2026-09-22—
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4213

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), Granite 3.1 8b Instruct: 34.5 (#233)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Coding14391186
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
ALE-Bench1,577—

Agentic & Tool Use GPT-6 Luna leads

GPT-6 Luna: 33.3 (#54), Granite 3.1 8b Instruct: 24.1 (#120)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
APEX-Agents44.3%—
Berkeley Function Calling Leaderboard—27.1%
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Granite 3.1 8b Instruct: 22.1 (#207)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Hard Prompts14111145
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
DTBench90.1%—
LMCA44.5%—
Epoch Capabilities Index156.28—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Granite 3.1 8b Instruct: 33.0 (#209)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Math14161152
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), Granite 3.1 8b Instruct: 31.1 (#220)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Expert14441142
GPQA Diamond90.5%—
SimpleQA Verified41.4%—

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Granite 3.1 8b Instruct: —

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Granite 3.1 8b Instruct: 30.9 (#260)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Non-English13861099
LMArena Chinese14331145
LMArena Russian13941092
LMArena French1420—
LMArena German1369—
LMArena Japanese1369—
LMArena Korean1360—
LMArena Spanish1393—

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Granite 3.1 8b Instruct: 58.6 (#259)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Instruction Following14091131

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Granite 3.1 8b Instruct: 35.2 (#241)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Longer Query14091162

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Granite 3.1 8b Instruct: 35.5 (#266)

BenchmarkGPT-6 LunaGranite 3.1 8b Instruct
LMArena Text13911150
LMArena Creative Writing13631129
LMArena Multi-Turn13961108

Frequently asked questions

Is GPT-6 Luna better than Granite 3.1 8b Instruct?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 32.4 on the Noometry Index.

Is GPT-6 Luna or Granite 3.1 8b Instruct better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 34.5 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Granite 3.1 8b Instruct share?

12 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Granite 3.1 8b Instruct has 13.

Related comparisons

Go deeper