Noometry

Model comparison

GPT-6 Luna vs Llama 2-70B

GPT-6 Luna is the stronger model overall, scoring 53.3 to 24.4 on the Noometry Index.

Last verified . 21 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-6 Luna scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 8.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for GPT-6 Luna and 0% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaLlama 2-70B
ProviderOpenAIMeta
Noometry Index53.324.4
Released2026-09-222023-07-18
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.50—
Results tracked4235

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), Llama 2-70B: 31.4 (#286)

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Coding14391079
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
ALE-Bench1,577—

Agentic & Tool Use Not comparable

GPT-6 Luna: 33.3 (#54), Llama 2-70B: —

BenchmarkGPT-6 LunaLlama 2-70B
APEX-Agents44.3%—
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Llama 2-70B: 14.4 (#325)

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Hard Prompts14111073
DTBench90.1%41.6%
Epoch Capabilities Index156.28113.79
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
Chess Puzzles31%—
Mystery Game Puzzles7%—
LMCA44.5%—
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%
WinoGrande—80.2%

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Llama 2-70B: 8.1 (#326)

BenchmarkGPT-6 LunaLlama 2-70B
OTIS Mock AIME 2024-202598.9%0%
LMArena Math14161091
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
ProofBench64%—
MATH Level 5—3.3%
GSM8K—69.6%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Llama 2-70B: 7.4 (#310)

BenchmarkGPT-6 LunaLlama 2-70B
GPQA Diamond90.5%26.3%
LMArena Expert14441039
SimpleQA Verified41.4%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Llama 2-70B: —

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Llama 2-70B: 27.7 (#274)

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Non-English13861045
LMArena Chinese1433995
LMArena French14201090
LMArena German13691041
LMArena Japanese1369927
LMArena Korean1360964
LMArena Russian13941083
LMArena Spanish13931143

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Llama 2-70B: 54.9 (#278)

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Instruction Following14091071

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Llama 2-70B: 32.3 (#270)

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Longer Query14091062

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Llama 2-70B: 32.3 (#279)

BenchmarkGPT-6 LunaLlama 2-70B
LMArena Text13911115
LMArena Creative Writing13631075
LMArena Multi-Turn13961088

Frequently asked questions

Is GPT-6 Luna better than Llama 2-70B?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 24.4 on the Noometry Index.

Is GPT-6 Luna or Llama 2-70B better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 31.4 in the Noometry coding category.

How many benchmarks do GPT-6 Luna and Llama 2-70B share?

21 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper