Noometry

Model comparison

GPT-6 Astra vs Nova 2.0 Pro Preview

GPT-6 Astra is the stronger model overall, scoring 70.8 to 33.4 on the Noometry Index.

Last verified . 3 shared benchmarks.

GPT-6 Astra OpenAI

70.8

Rank #1 Confirmed

Nova 2.0 Pro Preview Amazon

33.4

Rank #244 Reported

Summary

  • They share 3 benchmarks with published results for both. GPT-6 Astra scores higher in 3 categories and Nova 2.0 Pro Preview in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-6 Astra leads 85.1 to 22.4.
  • The biggest single-benchmark swing is GDP.pdf: 34.2% for GPT-6 Astra and 2% for Nova 2.0 Pro Preview.

Side by side

GPT-6 AstraNova 2.0 Pro Preview
ProviderOpenAIAmazon
Noometry Index70.833.4
Released2026-09-032025-12-02
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked563

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

Category by category

Coding GPT-6 Astra leads

GPT-6 Astra: 73.7 (#2), Nova 2.0 Pro Preview: 40.8 (#133)

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
SciCode56.5%42.7%
DeepSWE74.1%—
FrontierCode53.3%—
LMArena WebDev1786—
FrontierSWE65.5%—
GSO79.4%—
WeirdML93.6%—
LMArena Coding1487—
MirrorCode46.7%—
ALE-Bench2,951—

Agentic & Tool Use GPT-6 Astra leads

GPT-6 Astra: 52.9 (#3), Nova 2.0 Pro Preview: 21.9 (#136)

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
GDP.pdf34.2%2%
APEX-Agents64.7%—
Remote Labor Index20.8%—
BALROG68.3%—
Vending-Bench 215,515—

Reasoning GPT-6 Astra leads

GPT-6 Astra: 85.1 (#1), Nova 2.0 Pro Preview: 22.4 (#194)

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
CritPt31.7%0%
ARC-AGI-295%—
NYT Connections (extended)98.1%—
ARC-AGI-198.5%—
Chess Puzzles72%—
EBR-Bench76.2%—
LMArena Hard Prompts1462—
Mystery Game Puzzles84%—
DTBench97.3%—
LMCA64.4%—
Bench to the Future 30.14—
Epoch Capabilities Index166.45—

Math Not comparable

GPT-6 Astra: 93.5 (#2), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 497.6%—
OTIS Mock AIME 2024-2025100%—
ProofBench99%—
LMArena Math1465—
FrontierMath Erdős2.9%—

Knowledge Not comparable

GPT-6 Astra: 75.3 (#1), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
GPQA Diamond95.8%—
Humanity's Last Exam54.8%—
SimpleQA Verified75.6%—
Vectara Hallucination Rate8.7%—
LMArena Expert1483—

Multimodal Not comparable

GPT-6 Astra: 55.0 (#3), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
LMArena Vision1281—
Blueprint-Bench 249.7%—
Furniture Assembly80%—
LMArena Document1468—

Multilingual Not comparable

GPT-6 Astra: 53.7 (#61), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
LMArena Non-English1430—
LMArena Chinese1484—
LMArena French1456—
LMArena German1440—
LMArena Japanese1379—
LMArena Korean1426—
LMArena Russian1436—
LMArena Spanish1407—

Instruction Following Not comparable

GPT-6 Astra: 76.3 (#44), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
LMArena Instruction Following1450—

Long Context Not comparable

GPT-6 Astra: 44.5 (#62), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
LMArena Longer Query1456—

Writing & Preference Not comparable

GPT-6 Astra: 75.3 (#7), Nova 2.0 Pro Preview: —

BenchmarkGPT-6 AstraNova 2.0 Pro Preview
LMArena Text1441—
LMArena Creative Writing1418—
EQ-Bench Creative Writing2173—
LMArena Multi-Turn1448—

Frequently asked questions

Is GPT-6 Astra better than Nova 2.0 Pro Preview?

GPT-6 Astra is the stronger model overall, scoring 70.8 to 33.4 on the Noometry Index.

Is GPT-6 Astra or Nova 2.0 Pro Preview better for coding?

GPT-6 Astra scores higher on coding benchmarks: 73.7 versus 40.8 in the Noometry coding category.

How many benchmarks do GPT-6 Astra and Nova 2.0 Pro Preview share?

3 benchmarks have published results for both models. GPT-6 Astra has 56 scored results on Noometry and Nova 2.0 Pro Preview has 3.

Related comparisons

Go deeper