Noometry

Model comparison

GPT-6 Luna vs Phi-4

GPT-6 Luna is the stronger model overall, scoring 53.3 to 31.2 on the Noometry Index. Phi-4 costs 2.3× less per token, which makes it the better buy when GPT-6 Luna's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

GPT-6 Luna OpenAI

53.3

Rank #36 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GPT-6 Luna scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6 Luna leads 76.1 to 20.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for GPT-6 Luna and 13.8% for Phi-4.
  • Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.10 / $0.50 for GPT-6 Luna.
  • GPT-6 Luna accepts more context: 1.05M tokens versus 128K.
  • Phi-4 has downloadable open weights; the other is API-only.

Side by side

GPT-6 LunaPhi-4
ProviderOpenAIMicrosoft
Noometry Index53.331.2
Released2026-09-222024-12-11
WeightsProprietaryOpen
Context window1.05M128K
Max output128K4K
Input $ / M tokens$0.10$0.07
Output $ / M tokens$0.50$0.14
Results tracked4237

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), Phi-4: 34.4 (#239)

BenchmarkGPT-6 LunaPhi-4
LMArena Coding14391231
DeepSWE66.6%—
FrontierCode42.4%—
LMArena WebDev1581—
SciCode54.6%—
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%
ALE-Bench1,577—

Agentic & Tool Use GPT-6 Luna leads

GPT-6 Luna: 33.3 (#54), Phi-4: 22.8 (#128)

BenchmarkGPT-6 LunaPhi-4
APEX-Agents44.3%—
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%
GDP.pdf23%—

Reasoning GPT-6 Luna leads

GPT-6 Luna: 48.2 (#41), Phi-4: 17.7 (#291)

BenchmarkGPT-6 LunaPhi-4
Chess Puzzles31%1%
LMArena Hard Prompts14111220
Epoch Capabilities Index156.28130.42
ARC-AGI-259.3%—
NYT Connections (extended)68.7%—
ARC-AGI-186.7%—
CritPt19.4%—
LiveBench Reasoning—47.8%
Mystery Game Puzzles7%—
DTBench90.1%—
LiveBench Data Analysis—45.2%
LMCA44.5%—
LiveBench—41.6%

Math GPT-6 Luna leads

GPT-6 Luna: 76.1 (#15), Phi-4: 20.8 (#285)

BenchmarkGPT-6 LunaPhi-4
OTIS Mock AIME 2024-202598.9%13.8%
LMArena Math14161246
FrontierMath (Tiers 1-3)78.9%—
FrontierMath Tier 456.1%—
ProofBench64%—
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge GPT-6 Luna leads

GPT-6 Luna: 57.0 (#41), Phi-4: 32.6 (#209)

BenchmarkGPT-6 LunaPhi-4
GPQA Diamond90.5%56.1%
LMArena Expert14441203
SimpleQA Verified41.4%—
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multimodal Not comparable

GPT-6 Luna: 42.4 (#30), Phi-4: —

BenchmarkGPT-6 LunaPhi-4
LMArena Vision1217—
Blueprint-Bench 231.2%—
Furniture Assembly44.2%—

Multilingual GPT-6 Luna leads

GPT-6 Luna: 50.5 (#117), Phi-4: 37.2 (#237)

BenchmarkGPT-6 LunaPhi-4
LMArena Non-English13861197
LMArena Chinese14331212
LMArena French14201224
LMArena German13691222
LMArena Japanese13691158
LMArena Korean13601151
LMArena Russian13941209
LMArena Spanish13931234

Instruction Following GPT-6 Luna leads

GPT-6 Luna: 74.3 (#99), Phi-4: 60.4 (#251)

BenchmarkGPT-6 LunaPhi-4
LMArena Instruction Following14091201
LiveBench Instruction Following—58.4%

Long Context GPT-6 Luna leads

GPT-6 Luna: 43.0 (#111), Phi-4: 36.9 (#226)

BenchmarkGPT-6 LunaPhi-4
LMArena Longer Query14091217

Writing & Preference GPT-6 Luna leads

GPT-6 Luna: 58.3 (#119), Phi-4: 40.5 (#244)

BenchmarkGPT-6 LunaPhi-4
LMArena Text13911217
LMArena Creative Writing13631182
LMArena Multi-Turn13961206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is GPT-6 Luna better than Phi-4?

GPT-6 Luna is the stronger model overall, scoring 53.3 to 31.2 on the Noometry Index. Phi-4 costs 2.3× less per token, which makes it the better buy when GPT-6 Luna's lead doesn't matter for your workload.

Which is cheaper, GPT-6 Luna or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; GPT-6 Luna lists at $0.10 and $0.50.

Is GPT-6 Luna or Phi-4 better for coding?

GPT-6 Luna scores higher on coding benchmarks: 55.5 versus 34.4 in the Noometry coding category.

Which has the bigger context window?

GPT-6 Luna does, with 1.05M tokens against 128K.

How many benchmarks do GPT-6 Luna and Phi-4 share?

21 benchmarks have published results for both models. GPT-6 Luna has 42 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper