Noometry

Model comparison

GPT-6 Astra vs Laguna XS.2

GPT-6 Astra has enough public results to be ranked (#1); Laguna XS.2 does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

GPT-6 Astra OpenAI

70.3

Rank #1 Confirmed

Laguna XS.2 Poolside

32.5

Unranked Sparse

Summary

  • They share 2 benchmarks with published results for both. GPT-6 Astra scores higher in 2 categories and Laguna XS.2 in 0 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Astra leads 93.4 to 20.3.
  • The biggest single-benchmark swing is ProofBench: 99% for GPT-6 Astra and 0% for Laguna XS.2.
  • Laguna XS.2 has downloadable open weights; the other is API-only.

Side by side

GPT-6 AstraLaguna XS.2
ProviderOpenAIPoolside
Noometry Index70.332.5
Released2026-09-032026-04-28
WeightsProprietaryOpen
Context window1.05M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked512

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

Category by category

Coding GPT-6 Astra leads

GPT-6 Astra: 70.5 (#3), Laguna XS.2: 34.1

BenchmarkGPT-6 AstraLaguna XS.2
LMArena WebDev17921302
DeepSWE74.1%—
FrontierCode53.3%—
FrontierSWE65.5%—
SciCode56.5%—
WeirdML93.6%—
LMArena Coding1488—
MirrorCode46.7%—
ALE-Bench2,951—

Agentic & Tool Use Not comparable

GPT-6 Astra: 52.3 (#3), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
APEX-Agents64.7%—
Remote Labor Index20.8%—
BALROG68.3%—
Vending-Bench 215,515—

Reasoning Not comparable

GPT-6 Astra: 85.1 (#1), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
ARC-AGI-295%—
NYT Connections (extended)98.1%—
ARC-AGI-198.5%—
CritPt31.7%—
Chess Puzzles72%—
EBR-Bench76.2%—
LMArena Hard Prompts1464—
Mystery Game Puzzles84%—
DTBench97.3%—
LMCA64.4%—
Bench to the Future 30.14—
Epoch Capabilities Index166.6—

Math GPT-6 Astra leads

GPT-6 Astra: 93.4 (#1), Laguna XS.2: 20.3

BenchmarkGPT-6 AstraLaguna XS.2
ProofBench99%0%
FrontierMath (Tiers 1-3)93.7%—
FrontierMath Tier 497.6%—
OTIS Mock AIME 2024-2025100%—
LMArena Math1463—
FrontierMath Erdős2.9%—

Knowledge Not comparable

GPT-6 Astra: 75.3 (#1), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
GPQA Diamond95.8%—
Humanity's Last Exam54.8%—
SimpleQA Verified75.6%—
Vectara Hallucination Rate8.7%—
LMArena Expert1486—

Multimodal Not comparable

GPT-6 Astra: 55.1 (#3), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
LMArena Vision1280—
Blueprint-Bench 249.7%—
Furniture Assembly80%—
LMArena Document1468—

Multilingual Not comparable

GPT-6 Astra: 54.0 (#53), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
LMArena Non-English1431—
LMArena Chinese1495—
LMArena French1467—
LMArena Russian1434—
LMArena Spanish1412—

Instruction Following Not comparable

GPT-6 Astra: 76.6 (#37), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
LMArena Instruction Following1454—

Long Context Not comparable

GPT-6 Astra: 44.7 (#57), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
LMArena Longer Query1460—

Writing & Preference Not comparable

GPT-6 Astra: 75.7 (#7), Laguna XS.2: —

BenchmarkGPT-6 AstraLaguna XS.2
LMArena Text1443—
LMArena Creative Writing1423—
EQ-Bench Creative Writing2173—
LMArena Multi-Turn1457—

Frequently asked questions

Is GPT-6 Astra better than Laguna XS.2?

GPT-6 Astra has enough public results to be ranked (#1); Laguna XS.2 does not yet, so treat this comparison as directional.

Is GPT-6 Astra or Laguna XS.2 better for coding?

GPT-6 Astra scores higher on coding benchmarks: 70.5 versus 34.1 in the Noometry coding category.

How many benchmarks do GPT-6 Astra and Laguna XS.2 share?

2 benchmarks have published results for both models. GPT-6 Astra has 51 scored results on Noometry and Laguna XS.2 has 2.

Related comparisons

Go deeper