Noometry

Model comparison

Gemma 3 1B vs GPT-6 Astra

GPT-6 Astra is the stronger model overall, scoring 70.3 to 20.7 on the Noometry Index.

Last verified . 3 shared benchmarks.

Gemma 3 1B Google

20.7

Rank #348 Reported

GPT-6 Astra OpenAI

70.3

Rank #1 Confirmed

Summary

  • They share 3 benchmarks with published results for both. Gemma 3 1B scores higher in 0 categories and GPT-6 Astra in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Astra leads 93.4 to 9.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for Gemma 3 1B and 100% for GPT-6 Astra.
  • Gemma 3 1B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 1BGPT-6 Astra
ProviderGoogleOpenAI
Noometry Index20.770.3
Released2025-03-122026-09-03
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$10
Output $ / M tokens—$50
Results tracked451

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

Category by category

Coding Not comparable

Gemma 3 1B: —, GPT-6 Astra: 70.5 (#3)

BenchmarkGemma 3 1BGPT-6 Astra
DeepSWE—74.1%
FrontierCode—53.3%
LMArena WebDev—1792
FrontierSWE—65.5%
SciCode—56.5%
WeirdML—93.6%
LMArena Coding—1488
MirrorCode—46.7%
ALE-Bench—2,951

Agentic & Tool Use GPT-6 Astra leads

Gemma 3 1B: 13.5 (#144), GPT-6 Astra: 52.3 (#3)

BenchmarkGemma 3 1BGPT-6 Astra
APEX-Agents—64.7%
Berkeley Function Calling Leaderboard7.2%—
Remote Labor Index—20.8%
BALROG—68.3%
Vending-Bench 2—15,515

Reasoning GPT-6 Astra leads

Gemma 3 1B: 18.5 (#260), GPT-6 Astra: 85.1 (#1)

BenchmarkGemma 3 1BGPT-6 Astra
Chess Puzzles0%72%
ARC-AGI-2—95%
NYT Connections (extended)—98.1%
ARC-AGI-1—98.5%
CritPt—31.7%
EBR-Bench—76.2%
LMArena Hard Prompts—1464
Mystery Game Puzzles—84%
DTBench—97.3%
LMCA—64.4%
Bench to the Future 3—0.14
Epoch Capabilities Index—166.6

Math GPT-6 Astra leads

Gemma 3 1B: 9.6 (#310), GPT-6 Astra: 93.4 (#1)

BenchmarkGemma 3 1BGPT-6 Astra
OTIS Mock AIME 2024-20251.1%100%
FrontierMath (Tiers 1-3)—93.7%
FrontierMath Tier 4—97.6%
ProofBench—99%
LMArena Math—1463
FrontierMath Erdős—2.9%

Knowledge GPT-6 Astra leads

Gemma 3 1B: 7.1 (#309), GPT-6 Astra: 75.3 (#1)

BenchmarkGemma 3 1BGPT-6 Astra
GPQA Diamond19.9%95.8%
Humanity's Last Exam—54.8%
SimpleQA Verified—75.6%
Vectara Hallucination Rate—8.7%
LMArena Expert—1486

Multimodal Not comparable

Gemma 3 1B: —, GPT-6 Astra: 55.1 (#3)

BenchmarkGemma 3 1BGPT-6 Astra
LMArena Vision—1280
Blueprint-Bench 2—49.7%
Furniture Assembly—80%
LMArena Document—1468

Multilingual Not comparable

Gemma 3 1B: —, GPT-6 Astra: 54.0 (#53)

BenchmarkGemma 3 1BGPT-6 Astra
LMArena Non-English—1431
LMArena Chinese—1495
LMArena French—1467
LMArena Russian—1434
LMArena Spanish—1412

Instruction Following Not comparable

Gemma 3 1B: —, GPT-6 Astra: 76.6 (#37)

BenchmarkGemma 3 1BGPT-6 Astra
LMArena Instruction Following—1454

Long Context Not comparable

Gemma 3 1B: —, GPT-6 Astra: 44.7 (#57)

BenchmarkGemma 3 1BGPT-6 Astra
LMArena Longer Query—1460

Writing & Preference Not comparable

Gemma 3 1B: —, GPT-6 Astra: 75.7 (#7)

BenchmarkGemma 3 1BGPT-6 Astra
LMArena Text—1443
LMArena Creative Writing—1423
EQ-Bench Creative Writing—2173
LMArena Multi-Turn—1457

Frequently asked questions

Is Gemma 3 1B better than GPT-6 Astra?

GPT-6 Astra is the stronger model overall, scoring 70.3 to 20.7 on the Noometry Index.

How many benchmarks do Gemma 3 1B and GPT-6 Astra share?

3 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and GPT-6 Astra has 51.

Related comparisons

Go deeper