Noometry

Model comparison

GPT-6 Luna vs Qwen3-30B-A3B

GPT-6 Luna is the stronger model overall, scoring 53.3 to 38.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GPT-6 Luna scores higher in 9 categories and Qwen3-30B-A3B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 37.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for GPT-6 Luna and 70.3% for Qwen3-30B-A3B.
  • GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 41K.
  • Qwen3-30B-A3B has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaQwen3-30B-A3B
ProviderOpenAIAlibaba (Qwen)
Noometry Index53.338.9
Released2026-09-222025-04-28
WeightsProprietaryOpen
Context window1.05M41K
Max output128K16K
Input $ / M tokens$0.10$0.12
Output $ / M tokens$0.50$0.50
Results tracked4232

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

Category by category

Coding GPT-6 Luna leads

GPT-6 Luna: 55.5 (#25), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkGPT-6 LunaQwen3-30B-A3B
SciCode54.6%33.3%
LMArena Coding14391416
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
WeirdML—29.8%
ALE-Bench1,577—

Agentic & Tool Use GPT-6 Luna leads

GPT-6 Luna: 33.3 (#54), Qwen3-30B-A3B: 29.8 (#82)

BenchmarkGPT-6 LunaQwen3-30B-A3B
APEX-Agents44.3%—
Berkeley Function Calling Leaderboard—41.4%
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkGPT-6 LunaQwen3-30B-A3B
CritPt19.4%0.3%
Chess Puzzles31%8%
LMArena Hard Prompts14111398
DTBench90.1%69.3%
LMCA44.5%22.4%
Epoch Capabilities Index156.28139.63
ARC-AGI-259.3%—
Kagi LLM Benchmark—54.9%
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
Mystery Game Puzzles7%—

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Qwen3-30B-A3B: 37.4 (#157)

BenchmarkGPT-6 LunaQwen3-30B-A3B
OTIS Mock AIME 2024-202598.9%70.3%
LMArena Math14161394
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
MathArena Final-Answer Competitions—47.8%
ProofBench64%—

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Qwen3-30B-A3B: 41.8 (#105)

BenchmarkGPT-6 LunaQwen3-30B-A3B
GPQA Diamond90.5%70.1%
LMArena Expert14441396
SimpleQA Verified41.4%—
Confabulations—12.3%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Qwen3-30B-A3B: —

BenchmarkGPT-6 LunaQwen3-30B-A3B
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Qwen3-30B-A3B: 49.5 (#132)

BenchmarkGPT-6 LunaQwen3-30B-A3B
LMArena Non-English13861372
LMArena Chinese14331433
LMArena French14201418
LMArena German13691380
LMArena Japanese13691337
LMArena Korean13601331
LMArena Russian13941370
LMArena Spanish13931404

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Qwen3-30B-A3B: 72.0 (#142)

BenchmarkGPT-6 LunaQwen3-30B-A3B
LMArena Instruction Following14091363

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Qwen3-30B-A3B: 31.0 (#283)

BenchmarkGPT-6 LunaQwen3-30B-A3B
LMArena Longer Query14091379
Fiction.LiveBench—40.6%

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Qwen3-30B-A3B: 55.6 (#143)

BenchmarkGPT-6 LunaQwen3-30B-A3B
LMArena Text13911384
LMArena Creative Writing13631317
LMArena Multi-Turn13961378
Short-Story Creative Writing—75.3%

Frequently asked questions

Is GPT-6 Luna better than Qwen3-30B-A3B?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 38.9 on the Noometry Index.

Which is cheaper, GPT-6 Luna or Qwen3-30B-A3B?

GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.

Is GPT-6 Luna or Qwen3-30B-A3B better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 41K.

How many benchmarks do GPT-6 Luna and Qwen3-30B-A3B share?

25 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper