Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.4 mini vs GPT-5.6 Luna

Data verified

Head-to-head evidence from 22 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.77/100
Margin
10.4pts
winning →
67.17/100
0 category wins4 category wins

Public leaderboard positions: GPT-5.4 mini #75 (Estimated); GPT-5.6 Luna #22 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.4 mini and GPT-5.6 Luna share 22 comparable benchmark results. 4 of 8 categories are comparable. 8 results are unique to GPT-5.4 mini; 19 to GPT-5.6 Luna.

Updated July 23, 2026
Shared results
22
GPT-5.4 mini only
8
GPT-5.6 Luna only
19
Comparable categories
4 / 8

Pick GPT-5.6 Luna if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 22 shared benchmark results across 6 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GPT-5.6 Luna is clearly ahead on the BenchAlign aggregate, 67.17 to 56.77. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.6 Luna's sharpest advantage is in mathematics, where it averages 73.6 against 21.7. The single biggest benchmark swing on the page is FrontierMath v2 (Tier 4), 2.080% to 58.500%.

GPT-5.6 Luna is also the more expensive model on tokens at $1.00 input / $6.00 output per 1M tokens, versus $0.75 input / $4.50 output per 1M tokens for GPT-5.4 mini. GPT-5.6 Luna gives you the larger context window at 1M, compared with 400K for GPT-5.4 mini.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for GPT-5.4 mini and GPT-5.6 Luna
CategoryGPT-5.4 miniΔGPT-5.6 Luna
MathGPT-5.4 mini21.7Margin→ 51.9GPT-5.6 Luna73.6
KnowledgeGPT-5.4 mini47.8Margin→ 44.5GPT-5.6 Luna92.3
AgenticGPT-5.4 mini65.7Margin→ 18.4GPT-5.6 Luna84.1
MultimodalGPT-5.4 mini76.6Margin→ 1.8GPT-5.6 Luna78.4
CodingGPT-5.4 miniNot measuredMarginNo overlapGPT-5.6 Luna62.7

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · GPT-5.4 miniB · GPT-5.6 Luna

  1. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 2.080%B 58.500%
    Winner: GPT-5.6 LunaΔ 56.4
    FrontierMath v2 (Tier 4): GPT-5.4 mini scored 2.080%; GPT-5.6 Luna scored 58.500%. GPT-5.6 Luna wins this benchmark.

  2. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 28.280%B 78.600%
    Winner: GPT-5.6 LunaΔ 50.3
    FrontierMath v2 (Tiers 1-3): GPT-5.4 mini scored 28.280%; GPT-5.6 Luna scored 78.600%. GPT-5.6 Luna wins this benchmark.

  3. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 60%B 84.7%
    Winner: GPT-5.6 LunaΔ 24.7
    Terminal-Bench 2.0: GPT-5.4 mini scored 60%; GPT-5.6 Luna scored 84.7%. GPT-5.6 Luna wins this benchmark.

  4. GPQA

    Knowledge
    Source ↗
    A 88%B 92.3%
    Winner: GPT-5.6 LunaΔ 4.3
    GPQA: GPT-5.4 mini scored 88%; GPT-5.6 Luna scored 92.3%. GPT-5.6 Luna wins this benchmark.

  5. MMMU-Pro

    Multimodal
    Source ↗
    A 76.6%B 78.4%
    Winner: GPT-5.6 LunaΔ 1.8
    MMMU-Pro: GPT-5.4 mini scored 76.6%; GPT-5.6 Luna scored 78.4%. GPT-5.6 Luna wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGPT-5.4 miniGPT-5.6 LunaComparison
Input / output priceUSD per 1M tokensGPT-5.4 mini$0.75 input / $4.5 outputGPT-5.6 Luna$1 input / $6 outputGPT-5.4 mini has the lower combined listed price.
Generation speedtokens per secondGPT-5.4 mini201 tok/sGPT-5.6 LunaNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.4 mini3.85 sGPT-5.6 LunaNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.4 mini400KGPT-5.6 Luna1MGPT-5.6 Luna lists the larger context window.

Benchmark Deep Dive

AgenticGPT-5.6 Luna wins
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
Terminal-Bench 2.0Source 60%84.7%GPT-5.6 Luna leads
OSWorld-VerifiedSource 72.1%—Not comparable
MCP AtlasSource 57.7%—Not comparable
ToolathlonSource 42.9%53.4%GPT-5.6 Luna leads
τ²-bench resultsSource 83.3%—Not comparable
AA Agentic IndexSource 30.2%45.6%GPT-5.6 Luna leads
APEX-Agents-AASource 28.2%35.8%GPT-5.6 Luna leads
GDPval-AASource 33.6%54.2%GPT-5.6 Luna leads
GDPval-AASource 11711584GPT-5.6 Luna leads
BrowseCompSource —83.3%Not comparable
OSWorld 2.0Source —45.6%Not comparable
CyberGymSource —77.9%Not comparable
ExploitGymSource —12.4%Not comparable
AA Harvey LABSource —87.9%Not comparable
AA ITBenchSource —40.3%Not comparable
AA Tau3 BankingSource —27.2%Not comparable
AA AutomationBenchSource —42.2%Not comparable
aaTerminalBench21Source —80.9%Not comparable
Coding
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
Vibe Code BenchSource 47.97%—Not comparable
AA Coding IndexSource 56.1%71.5%GPT-5.6 Luna leads
AA-SciCodeSource 49.9%52.5%GPT-5.6 Luna leads
FrontierCode 1.1 MainSource 27.0%—Not comparable
SWE-bench ProSource —62.7%Not comparable
Terminal-Bench 2.0Source —84.7%Not comparable
deepSweSource —67.2%Not comparable
FrontierCode 1.1 ExtendedSource —55.1%Not comparable
cursorBench32Source —61.1%Not comparable
Reasoning
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
AA-LCRSource 69.3%74.0%GPT-5.6 Luna leads
CritPtSource 10.0%20.6%GPT-5.6 Luna leads
ARC-AGI-3Source —0.2%Not comparable
KnowledgeGPT-5.6 Luna wins
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
GPQASource 88%92.3%GPT-5.6 Luna leads
HLESource 41.5%—Not comparable
HLE w/o toolsSource 28.2%—Not comparable
Artificial Analysis Intelligence IndexSource 40.0%51.2%GPT-5.6 Luna leads
AA-GPQA DiamondSource 87.5%91.1%GPT-5.6 Luna leads
AA-HLESource 26.6%37.2%GPT-5.6 Luna leads
AA-Omniscience IndexSource -18.7%-11.2%GPT-5.6 Luna leads
AA-Omniscience AccuracySource 37.5%41.5%GPT-5.6 Luna leads
AA-Omniscience Hallucination RateSource 89.8%90.1%GPT-5.4 mini leads
GPQA-DSource —92.3%Not comparable
HealthBench ProfessionalSource —55.7%Not comparable
HealthBench HardSource —32.0%Not comparable
MathGPT-5.6 Luna wins
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
FrontierMath v2 (Tiers 1-3)Source 28.280%78.600%GPT-5.6 Luna leads
FrontierMath v2 (Tier 4)Source 2.080%58.500%GPT-5.6 Luna leads
FrontierMath (legacy)Source —78.6%Not comparable
MultimodalGPT-5.6 Luna wins
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
MMMU-ProSource 76.6%78.4%GPT-5.6 Luna leads
MMMU-Pro w/ PythonSource 78%79.5%GPT-5.6 Luna leads
AA-MMMU-ProSource 73.3%78.6%GPT-5.6 Luna leads
Inst. Following
BenchmarkGPT-5.4 miniGPT-5.6 LunaResult
AA-IFBenchSource 73.3%—Not comparable
Frequently Asked Questions (5)

Which is better, GPT-5.4 mini or GPT-5.6 Luna?

GPT-5.6 Luna is ahead on BenchLM's BenchAlign leaderboard, 67.17 to 56.77. The biggest single separator in this matchup is FrontierMath v2 (Tier 4), where the scores are 2.080% and 58.500%.

Which is better for knowledge tasks, GPT-5.4 mini or GPT-5.6 Luna?

GPT-5.6 Luna has the edge for knowledge tasks in this comparison, averaging 92.3 versus 47.8. Inside this category, Artificial Analysis Intelligence Index is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.4 mini or GPT-5.6 Luna?

GPT-5.6 Luna has the edge for math in this comparison, averaging 73.6 versus 21.7. Inside this category, FrontierMath v2 (Tier 4) is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.4 mini or GPT-5.6 Luna?

GPT-5.6 Luna has the edge for agentic tasks in this comparison, averaging 84.1 versus 65.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.4 mini or GPT-5.6 Luna?

GPT-5.6 Luna has the edge for multimodal and grounded tasks in this comparison, averaging 78.4 versus 76.6. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

OpenAI Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.