Noometry

Model comparison

C4ai Aya Expanse 8b vs GPT-6 Luna

GPT-6 Luna is the stronger model overall, scoring 53.3 to 34.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

C4ai Aya Expanse 8b Cohere

34.9

Rank #229 Confirmed

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Summary

  • They share 14 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 0 categories and GPT-6 Luna in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 33.3.
  • C4ai Aya Expanse 8b has downloadable open weights; the other is API-only.

Side by side

C4ai Aya Expanse 8bGPT-6 Luna
ProviderCohereOpenAI
Noometry Index34.953.3
Released—2026-09-22
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.50
Results tracked1542

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

Category by category

Coding GPT-6 Luna leads

C4ai Aya Expanse 8b: 33.8 (#252), GPT-6 Luna: 55.5 (#25)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Coding11601439
DeepSWE—66.6%
FrontierCode—42.4%
LMArena WebDev—1581
SciCode—54.6%
ALE-Bench—1,577

Agentic & Tool Use Not comparable

C4ai Aya Expanse 8b: —, GPT-6 Luna: 33.3 (#54)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
APEX-Agents—44.3%
GDP.pdf—23%

Reasoning GPT-6 Luna leads

C4ai Aya Expanse 8b: 22.4 (#197), GPT-6 Luna: 48.2 (#41)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Hard Prompts11561411
ARC-AGI-2—59.3%
NYT Connections (extended)—68.7%
ARC-AGI-1—86.7%
CritPt—19.4%
Chess Puzzles—31%
Mystery Game Puzzles—7%
DTBench—90.1%
LMCA—44.5%
Epoch Capabilities Index—156.28

Math GPT-6 Luna leads

C4ai Aya Expanse 8b: 33.3 (#203), GPT-6 Luna: 76.1 (#15)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Math11681416
FrontierMath (Tiers 1-3)—78.9%
FrontierMath Tier 4—56.1%
OTIS Mock AIME 2024-2025—98.9%
ProofBench—64%

Knowledge GPT-6 Luna leads

C4ai Aya Expanse 8b: 33.6 (#201), GPT-6 Luna: 57.0 (#41)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Expert11531444
GPQA Diamond—90.5%
SimpleQA Verified—41.4%
Vectara Hallucination Rate9.5%—

Multimodal Not comparable

C4ai Aya Expanse 8b: —, GPT-6 Luna: 42.4 (#30)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Vision—1217
Blueprint-Bench 2—31.2%
Furniture Assembly—44.2%

Multilingual GPT-6 Luna leads

C4ai Aya Expanse 8b: 36.1 (#242), GPT-6 Luna: 50.5 (#117)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Non-English11801386
LMArena Chinese11811433
LMArena German11881369
LMArena Japanese11201369
LMArena Russian11971394
LMArena French—1420
LMArena Korean—1360
LMArena Spanish—1393

Instruction Following GPT-6 Luna leads

C4ai Aya Expanse 8b: 60.1 (#253), GPT-6 Luna: 74.3 (#99)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Instruction Following11551409

Long Context GPT-6 Luna leads

C4ai Aya Expanse 8b: 36.1 (#236), GPT-6 Luna: 43.0 (#111)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Longer Query11911409

Writing & Preference GPT-6 Luna leads

C4ai Aya Expanse 8b: 39.0 (#250), GPT-6 Luna: 58.3 (#119)

BenchmarkC4ai Aya Expanse 8bGPT-6 Luna
LMArena Text11851391
LMArena Creative Writing11681363
LMArena Multi-Turn11601396

Frequently asked questions

Is C4ai Aya Expanse 8b better than GPT-6 Luna?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 34.9 on the Noometry Index.

Is C4ai Aya Expanse 8b or GPT-6 Luna better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 33.8 in the Noometry coding category.

How many benchmarks do C4ai Aya Expanse 8b and GPT-6 Luna share?

14 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and GPT-6 Luna has 42.

Related comparisons

Go deeper