Noometry

Model comparison

Codellama 70b Instruct vs GPT-6 Astra

GPT-6 Astra is the stronger model overall, scoring 70.3 to 33.3 on the Noometry Index.

Last verified . 4 shared benchmarks.

Codellama 70b Instruct Meta

33.3

Rank #236 Confirmed

GPT-6 Astra OpenAI

70.3

Rank #1 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and GPT-6 Astra in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 19.2.
  • Codellama 70b Instruct has downloadable open weights; the other is API-only.

Side by side

Codellama 70b InstructGPT-6 Astra
ProviderMetaOpenAI
Noometry Index33.370.3
Released—2026-09-03
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$10
Output $ / M tokens—$50
Results tracked751

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

Category by category

Coding GPT-6 Astra leads

Codellama 70b Instruct: 37.0 (#189), GPT-6 Astra: 70.5 (#3)

BenchmarkCodellama 70b InstructGPT-6 Astra
DeepSWE—74.1%
FrontierCode—53.3%
LMArena WebDev—1792
FrontierSWE—65.5%
SciCode—56.5%
WeirdML—93.6%
BigCodeBench Instruct40.7%—
LMArena Coding—1488
MirrorCode—46.7%
BigCodeBench Complete49.6%—
ALE-Bench—2,951
HumanEval+65.9%—

Agentic & Tool Use Not comparable

Codellama 70b Instruct: —, GPT-6 Astra: 52.3 (#3)

BenchmarkCodellama 70b InstructGPT-6 Astra
APEX-Agents—64.7%
Remote Labor Index—20.8%
BALROG—68.3%
Vending-Bench 2—15,515

Reasoning GPT-6 Astra leads

Codellama 70b Instruct: 19.2 (#241), GPT-6 Astra: 85.1 (#1)

BenchmarkCodellama 70b InstructGPT-6 Astra
LMArena Hard Prompts10521464
ARC-AGI-2—95%
NYT Connections (extended)—98.1%
ARC-AGI-1—98.5%
CritPt—31.7%
Chess Puzzles—72%
EBR-Bench—76.2%
Mystery Game Puzzles—84%
DTBench—97.3%
LMCA—64.4%
Bench to the Future 3—0.14
Epoch Capabilities Index—166.6

Math Not comparable

Codellama 70b Instruct: —, GPT-6 Astra: 93.4 (#1)

BenchmarkCodellama 70b InstructGPT-6 Astra
FrontierMath (Tiers 1-3)—93.7%
FrontierMath Tier 4—97.6%
OTIS Mock AIME 2024-2025—100%
ProofBench—99%
LMArena Math—1463
FrontierMath Erdős—2.9%

Knowledge Not comparable

Codellama 70b Instruct: —, GPT-6 Astra: 75.3 (#1)

BenchmarkCodellama 70b InstructGPT-6 Astra
GPQA Diamond—95.8%
Humanity's Last Exam—54.8%
SimpleQA Verified—75.6%
Vectara Hallucination Rate—8.7%
LMArena Expert—1486

Multimodal Not comparable

Codellama 70b Instruct: —, GPT-6 Astra: 55.1 (#3)

BenchmarkCodellama 70b InstructGPT-6 Astra
LMArena Vision—1280
Blueprint-Bench 2—49.7%
Furniture Assembly—80%
LMArena Document—1468

Multilingual GPT-6 Astra leads

Codellama 70b Instruct: 24.9 (#283), GPT-6 Astra: 54.0 (#53)

BenchmarkCodellama 70b InstructGPT-6 Astra
LMArena Non-English9921431
LMArena Chinese—1495
LMArena French—1467
LMArena Russian—1434
LMArena Spanish—1412

Instruction Following GPT-6 Astra leads

Codellama 70b Instruct: 52.1 (#288), GPT-6 Astra: 76.6 (#37)

BenchmarkCodellama 70b InstructGPT-6 Astra
LMArena Instruction Following10241454

Long Context Not comparable

Codellama 70b Instruct: —, GPT-6 Astra: 44.7 (#57)

BenchmarkCodellama 70b InstructGPT-6 Astra
LMArena Longer Query—1460

Writing & Preference GPT-6 Astra leads

Codellama 70b Instruct: 33.6 (#272), GPT-6 Astra: 75.7 (#7)

BenchmarkCodellama 70b InstructGPT-6 Astra
LMArena Text10571443
LMArena Creative Writing—1423
EQ-Bench Creative Writing—2173
LMArena Multi-Turn—1457

Frequently asked questions

Is Codellama 70b Instruct better than GPT-6 Astra?

GPT-6 Astra is the stronger model overall, scoring 70.3 to 33.3 on the Noometry Index.

Is Codellama 70b Instruct or GPT-6 Astra better for coding?

GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 37.0 in the Noometry coding category.

How many benchmarks do Codellama 70b Instruct and GPT-6 Astra share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and GPT-6 Astra has 51.

Related comparisons

Go deeper