Skip to main content
BenchLM
Advertise

Model comparison

Kimi K2.5 vs Soofi S 30B-A3B

Data verified

Head-to-head evidence from 3 shared benchmark results across 1 category. Overall scores shown here use BenchLM's provisional ranking lane.

Kimi K2.5
Moonshot AI
61/100
Margin
16.0pts
← winning
Soofi S 30B-A3B
Soofi Project
45/100
1 category wins0 category wins

Verified leaderboard positions: Kimi K2.5 #23; Soofi S 30B-A3B unranked

Evidence parity. Kimi K2.5 and Soofi S 30B-A3B share 3 comparable benchmark results. 1 of 8 categories are comparable. 61 results are unique to Kimi K2.5; 5 to Soofi S 30B-A3B.

Updated July 15, 2026
Shared results
3
Kimi K2.5 only
61
Soofi S 30B-A3B only
5
Comparable categories
1 / 8

Pick Kimi K2.5 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 need the larger 1M context window.

Confidence note. This is a partial-evidence comparison with 3 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

Kimi K2.5 is clearly ahead on the provisional aggregate, 61 to 45. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Kimi K2.5's sharpest advantage is in knowledge, where it averages 57.2 against 49.9. The single biggest benchmark swing on the page is GPQA, 87.6% to 43.4%.

Kimi K2.5 is also the more expensive model on tokens at $0.60 input / $3.00 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. Soofi S 30B-A3B gives you the larger context window at 1M, compared with 256K for Kimi K2.5.

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 Kimi K2.5 and Soofi S 30B-A3B
CategoryKimi K2.5ΔSoofi S 30B-A3B
KnowledgeKimi K2.557.2Margin← 7.3Soofi S 30B-A3B49.9
AgenticKimi K2.555.0MarginNo overlapSoofi S 30B-A3BNot measured
CodingKimi K2.558.3MarginNo overlapSoofi S 30B-A3BNot measured
ReasoningKimi K2.561.0MarginNo overlapSoofi S 30B-A3BNot measured
MathKimi K2.560.6MarginNo overlapSoofi S 30B-A3BNot measured
MultilingualKimi K2.582.3MarginNo overlapSoofi S 30B-A3BNot measured
MultimodalKimi K2.578.5MarginNo overlapSoofi S 30B-A3BNot measured
Inst. FollowingKimi K2.593.9MarginNo overlapSoofi S 30B-A3BNot measured

Decisive benchmark drivers

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

More
A · Kimi K2.5B · Soofi S 30B-A3B

  1. GPQA

    Knowledge
    Source ↗
    A 87.6%B 43.4%
    Winner: Kimi K2.5Δ 44.2
    GPQA: Kimi K2.5 scored 87.6%; Soofi S 30B-A3B scored 43.4%. Kimi K2.5 wins this benchmark.

  2. MMLU-Pro

    Knowledge
    Source ↗
    A 87.1%B 51.4%
    Winner: Kimi K2.5Δ 35.7
    MMLU-Pro: Kimi K2.5 scored 87.1%; Soofi S 30B-A3B scored 51.4%. Kimi K2.5 wins this benchmark.

Operational comparison

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

MetricKimi K2.5Soofi S 30B-A3BComparison
Input / output priceUSD per 1M tokensKimi K2.5$0.6 input / $3 outputSoofi S 30B-A3B$0 input / $0 outputSoofi S 30B-A3B has the lower combined listed price.
Generation speedtokens per secondKimi K2.545 tok/sSoofi S 30B-A3BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenKimi K2.52.38 sSoofi S 30B-A3BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensKimi K2.5256KSoofi S 30B-A3B1MSoofi S 30B-A3B lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkKimi K2.5Soofi S 30B-A3BResult
Terminal-Bench 2.0Source 50.8%—Not comparable
BrowseCompSource 60.6%—Not comparable
Claw-EvalSource 52.3%—Not comparable
QwenClawBenchSource 54.3%—Not comparable
τ³-bench resultsSource 65.7%—Not comparable
DeepSearchQASource 77.1%—Not comparable
DeepPlanningSource 14.4%—Not comparable
ToolathlonSource 27.8%—Not comparable
MCP AtlasSource 29.5%—Not comparable
MCP-TasksSource 59.1%—Not comparable
WideResearchSource 72.7%—Not comparable
τ²-bench resultsSource 95.9%—Not comparable
APEX-Agents-AASource 11.5%—Not comparable
Gert LabsSource 45.88%—Not comparable
ResearchClawBenchSource 14.0%—Not comparable
JobBenchSource 8.7%—Not comparable
AA Agentic IndexSource 21.7%—Not comparable
GDPval-AASource 25.4%—Not comparable
GDPval-AASource 1009—Not comparable
Coding
BenchmarkKimi K2.5Soofi S 30B-A3BResult
SWE-bench VerifiedSource 76.8%—Not comparable
SWE-bench Verified*Source 70.8%—Not comparable
LiveCodeBench v6Source 85.0%—Not comparable
SWE-bench ProSource 50.7%—Not comparable
SWE MultilingualSource 73%—Not comparable
SWE-RebenchSource 58.5%—Not comparable
React Native EvalsSource 77.2%—Not comparable
SciCodeSource 48.7%—Not comparable
Terminal-Bench HardSource 34.8%—Not comparable
AA-SciCodeSource 49.0%—Not comparable
AA Coding IndexSource 46.8%—Not comparable
HumanEvalSource —73.8%Not comparable
Reasoning
BenchmarkKimi K2.5Soofi S 30B-A3BResult
LongBench v2Source 61%—Not comparable
AA-LCRSource 65.3%—Not comparable
CritPtSource 3.1%—Not comparable
BBHSource —78.8%Not comparable
DROPSource —66.5%Not comparable
KnowledgeKimi K2.5 wins
BenchmarkKimi K2.5Soofi S 30B-A3BResult
GPQASource 87.6%43.4%Kimi K2.5 leads
GPQA-DSource 87.6%43.4%Kimi K2.5 leads
SuperGPQASource 69.2%—Not comparable
MMLU-ProSource 87.1%51.4%Kimi K2.5 leads
MMLU-Pro (Arcee)Source 87.1%—Not comparable
HLESource 30.1%—Not comparable
Artificial Analysis Intelligence IndexSource 35.4%—Not comparable
AA-GPQA DiamondSource 87.9%—Not comparable
AA-HLESource 29.4%—Not comparable
AA-Omniscience IndexSource -8.1%—Not comparable
AA-Omniscience AccuracySource 34.3%—Not comparable
AA-Omniscience Hallucination RateSource 64.6%—Not comparable
AGIEvalSource —66.9%Not comparable
Math
BenchmarkKimi K2.5Soofi S 30B-A3BResult
AIME 2025Source 96.1%—Not comparable
AIME26Source 95.8%—Not comparable
AIME25 (Arcee)Source 96.3%—Not comparable
HMMT Feb 2025Source 95.4%—Not comparable
HMMT Nov 2025Source 91.1%—Not comparable
HMMT Feb 2026Source 87.1%—Not comparable
MMAnswerBenchSource 81.8%—Not comparable
FrontierMath v2 (Tiers 1-3)Source 27.900%—Not comparable
FrontierMath v2 (Tier 4)Source 4.200%—Not comparable
GSM8KSource —86.1%Not comparable
Multilingual
BenchmarkKimi K2.5Soofi S 30B-A3BResult
MMLU-ProXSource 82.3%—Not comparable
NOVA-63Source 56.0%—Not comparable
Multimodal
BenchmarkKimi K2.5Soofi S 30B-A3BResult
MMMU-ProSource 78.5%—Not comparable
Video-MMESource 87.4%—Not comparable
MMVUSource 80.4%—Not comparable
VideoMMMUSource 86.6%—Not comparable
AA-MMMU-ProSource 75.4%—Not comparable
Design Arena WebsiteSource 1284—Not comparable
Inst. Following
BenchmarkKimi K2.5Soofi S 30B-A3BResult
IFEvalSource 93.9%—Not comparable
AA-IFBenchSource 70.2%—Not comparable
Frequently Asked Questions (2)

Which is better, Kimi K2.5 or Soofi S 30B-A3B?

Kimi K2.5 is ahead on BenchLM's provisional leaderboard, 61 to 45. The biggest single separator in this matchup is GPQA, where the scores are 87.6% and 43.4%.

Which is better for knowledge tasks, Kimi K2.5 or Soofi S 30B-A3B?

Kimi K2.5 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 49.9. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Kimi K2.5
API / mo$2,700
Self-host / mo$5,221
Break-even132M/day
Soofi S 30B-A3B
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Model the full break-even

Related Comparisons

Explore More

Moonshot AI Compare Pricing Methodology Find Your Best LLM Overall Rankings
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.