Skip to main content

Model comparison

GPT-5.6 Luna vs Soofi S 30B-A3B

Data verified

Head-to-head evidence from 2 shared benchmark results across 1 category. Overall scores shown here use BenchLM's provisional ranking lane.

82/100
Margin
37.0pts
← winning
Soofi Project
45/100
1 category wins0 category wins

Evidence parity. GPT-5.6 Luna and Soofi S 30B-A3B share 2 comparable benchmark results. 1 of 8 categories are comparable. 38 results are unique to GPT-5.6 Luna; 6 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
2
GPT-5.6 Luna only
38
Soofi S 30B-A3B only
6
Comparable categories
1 / 8

Pick GPT-5.6 Luna if you want the stronger benchmark profile. Soofi S 30B-A3B only becomes the better choice if you want the cheaper token bill or you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 1 evidence category; 1 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 provisional aggregate, 82 to 45. 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 knowledge, where it averages 92.3 against 49.9. The single biggest benchmark swing on the page is GPQA, 92.3% to 43.4%.

GPT-5.6 Luna is also the more expensive model on tokens at $1.00 input / $6.00 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Soofi S 30B-A3B. That is roughly Infinityx on output cost alone. GPT-5.6 Luna is the reasoning model in the pair, while Soofi S 30B-A3B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

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-5.6 Luna and Soofi S 30B-A3B
CategoryGPT-5.6 LunaΔSoofi S 30B-A3B
KnowledgeGPT-5.6 Luna92.3Margin 42.4Soofi S 30B-A3B49.9
AgenticGPT-5.6 Luna84.1MarginNo overlapSoofi S 30B-A3BNot measured
CodingGPT-5.6 Luna62.7MarginNo overlapSoofi S 30B-A3BNot measured
MathGPT-5.6 Luna73.6MarginNo overlapSoofi S 30B-A3BNot measured
MultimodalGPT-5.6 Luna78.4MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · GPT-5.6 LunaB · Soofi S 30B-A3B
  1. GPQA

    Knowledge
    Source ↗
    A 92.3%B 43.4%
    Winner: GPT-5.6 LunaΔ 48.9
    GPQA: GPT-5.6 Luna scored 92.3%; Soofi S 30B-A3B scored 43.4%. 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-5.6 LunaSoofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensGPT-5.6 Luna$1 input / $6 outputSoofi S 30B-A3B$0 input / $0 outputSoofi S 30B-A3B has the lower combined listed price.
Generation speedtokens per secondGPT-5.6 LunaNot availableSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.6 LunaNot availableSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.6 Luna1MSoofi S 30B-A3B1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGPT-5.6 LunaSoofi S 30B-A3BResult
Terminal-Bench 2.0Source 84.7%Not comparable
BrowseCompSource 83.3%Not comparable
OSWorld 2.0Source 45.6%Not comparable
CyberGymSource 77.9%Not comparable
ExploitGymSource 12.4%Not comparable
ToolathlonSource 53.4%Not comparable
AA Agentic IndexSource 45.6%Not comparable
GDPval-AASource 54.6%Not comparable
GDPval-AASource 1592Not comparable
AA Harvey LABSource 5.0%Not comparable
AA ITBenchSource 40.3%Not comparable
AA Tau3 BankingSource 27.2%Not comparable
AA AutomationBenchSource 42.2%Not comparable
Coding
BenchmarkGPT-5.6 LunaSoofi S 30B-A3BResult
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
AA Coding IndexSource 71.5%Not comparable
AA-SciCodeSource 52.5%Not comparable
AA Terminal-Bench 2.1Source 80.9%Not comparable
HumanEvalSource 73.8%Not comparable
Reasoning
BenchmarkGPT-5.6 LunaSoofi S 30B-A3BResult
ARC-AGI-3Source 0.2%Not comparable
AA-LCRSource 74.0%Not comparable
CritPtSource 20.6%Not comparable
BBHSource 78.8%Not comparable
DROPSource 66.5%Not comparable
KnowledgeGPT-5.6 Luna wins
BenchmarkGPT-5.6 LunaSoofi S 30B-A3BResult
GPQASource 92.3%43.4%GPT-5.6 Luna leads
GPQA-DSource 92.3%43.4%GPT-5.6 Luna leads
HealthBench ProfessionalSource 55.7%Not comparable
HealthBench HardSource 32.0%Not comparable
Artificial Analysis Intelligence IndexSource 51.2%Not comparable
AA-GPQA DiamondSource 91.1%Not comparable
AA-HLESource 37.2%Not comparable
AA-Omniscience IndexSource -11.2%Not comparable
AA-Omniscience AccuracySource 41.5%Not comparable
AA-Omniscience Hallucination RateSource 90.1%Not comparable
MMLU-ProSource 51.4%Not comparable
AGIEvalSource 66.9%Not comparable
Math
BenchmarkGPT-5.6 LunaSoofi S 30B-A3BResult
FrontierMath (legacy)Source 78.6%Not comparable
FrontierMath v2 (Tiers 1-3)Source 78.600%Not comparable
FrontierMath v2 (Tier 4)Source 58.500%Not comparable
GSM8KSource 86.1%Not comparable
Multimodal
BenchmarkGPT-5.6 LunaSoofi S 30B-A3BResult
MMMU-ProSource 78.4%Not comparable
MMMU-Pro w/ PythonSource 79.5%Not comparable
AA-MMMU-ProSource 78.6%Not comparable
Frequently Asked Questions (2)

Which is better, GPT-5.6 Luna or Soofi S 30B-A3B?

GPT-5.6 Luna is ahead on BenchLM's provisional leaderboard, 82 to 45. The biggest single separator in this matchup is GPQA, where the scores are 92.3% and 43.4%.

Which is better for knowledge tasks, GPT-5.6 Luna or Soofi S 30B-A3B?

GPT-5.6 Luna has the edge for knowledge tasks in this comparison, averaging 92.3 versus 49.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.