Noometry

Model comparison

Gemma 2B vs GPT-6 Astra

GPT-6 Astra is the stronger model overall, scoring 70.8 to 29.6 on the Noometry Index.

Last verified . 12 shared benchmarks.

Gemma 2B Google

29.6

Rank #307 Confirmed

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and GPT-6 Astra in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 18.8.
  • Gemma 2B has downloadable open weights; the other is API-only.

Side by side

Gemma 2BGPT-6 Astra
ProviderGoogleOpenAI
Noometry Index29.670.8
Released2024-02-212026-09-03
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$10
Output $ / M tokens—$50
Results tracked2356

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

Category by category

Coding GPT-6 Astra leads

Gemma 2B: 29.4 (#305), GPT-6 Astra: 73.7 (#2)

BenchmarkGemma 2BGPT-6 Astra
LMArena Coding10101487
DeepSWE—74.1%
FrontierCode—53.3%
LMArena WebDev—1786
FrontierSWE—65.5%
SciCode—56.5%
GSO—79.4%
WeirdML—93.6%
MirrorCode—46.7%
ALE-Bench—2,951
HumanEval+20.7%—
MBPP+34.1%—

Agentic & Tool Use Not comparable

Gemma 2B: —, GPT-6 Astra: 52.9 (#3)

BenchmarkGemma 2BGPT-6 Astra
APEX-Agents—64.7%
Remote Labor Index—20.8%
BALROG—68.3%
GDP.pdf—34.2%
Vending-Bench 2—15,515

Reasoning GPT-6 Astra leads

Gemma 2B: 18.8 (#275), GPT-6 Astra: 85.1 (#1)

BenchmarkGemma 2BGPT-6 Astra
LMArena Hard Prompts9891462
Epoch Capabilities Index94.2166.45
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
BIG-Bench Hard35.2%—
HellaSwag71.4%—
PIQA77.3%—
WinoGrande65.4%—

Math GPT-6 Astra leads

Gemma 2B: 30.0 (#239), GPT-6 Astra: 93.5 (#2)

BenchmarkGemma 2BGPT-6 Astra
LMArena Math10091465
FrontierMath (Tiers 1-3)—93.7%
FrontierMath Tier 4—97.6%
OTIS Mock AIME 2024-2025—100%
ProofBench—99%
FrontierMath Erdős—2.9%
GSM8K17.7%—

Knowledge Not comparable

Gemma 2B: —, GPT-6 Astra: 75.3 (#1)

BenchmarkGemma 2BGPT-6 Astra
GPQA Diamond—95.8%
Humanity's Last Exam—54.8%
SimpleQA Verified—75.6%
Vectara Hallucination Rate—8.7%
LMArena Expert—1483
ARC (AI2) Challenge42.1%—
BoolQ69.4%—
MMLU42.3%—
TriviaQA53.2%—

Multimodal Not comparable

Gemma 2B: —, GPT-6 Astra: 55.0 (#3)

BenchmarkGemma 2BGPT-6 Astra
LMArena Vision—1281
Blueprint-Bench 2—49.7%
Furniture Assembly—80%
LMArena Document—1468

Multilingual GPT-6 Astra leads

Gemma 2B: 23.0 (#294), GPT-6 Astra: 53.7 (#61)

BenchmarkGemma 2BGPT-6 Astra
LMArena Non-English9581430
LMArena Chinese9861484
LMArena Russian9371436
LMArena French—1456
LMArena German—1440
LMArena Japanese—1379
LMArena Korean—1426
LMArena Spanish—1407

Instruction Following GPT-6 Astra leads

Gemma 2B: 48.5 (#302), GPT-6 Astra: 76.3 (#44)

BenchmarkGemma 2BGPT-6 Astra
LMArena Instruction Following9701450

Long Context GPT-6 Astra leads

Gemma 2B: 29.9 (#291), GPT-6 Astra: 44.5 (#62)

BenchmarkGemma 2BGPT-6 Astra
LMArena Longer Query9811456

Writing & Preference GPT-6 Astra leads

Gemma 2B: 24.0 (#308), GPT-6 Astra: 75.3 (#7)

BenchmarkGemma 2BGPT-6 Astra
LMArena Text10021441
LMArena Creative Writing9871418
LMArena Multi-Turn9451448
EQ-Bench Creative Writing—2173

Frequently asked questions

Is Gemma 2B better than GPT-6 Astra?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 29.6 on the Noometry Index.

Is Gemma 2B or GPT-6 Astra better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 29.4 in the Noometry coding category.

How many benchmarks do Gemma 2B and GPT-6 Astra share?

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GPT-6 Astra has 56.

Related comparisons

Go deeper