Skip to main content

Model comparison

DeepSeek V3.2 vs Kimi K2.7 Code

Data verified

Head-to-head evidence from 12 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

55.4/100
Margin
0.4pts
← winning
Moonshot AI
55/100
0 category wins0 category wins

Public leaderboard positions: DeepSeek V3.2 #82 (Supported); Kimi K2.7 Code #87 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. DeepSeek V3.2 and Kimi K2.7 Code share 12 comparable benchmark results. 0 of 8 categories are comparable. 7 results are unique to DeepSeek V3.2; 11 to Kimi K2.7 Code.

Updated July 23, 2026
Shared results
12
DeepSeek V3.2 only
7
Kimi K2.7 Code only
11
Comparable categories
0 / 8

Benchmark data for DeepSeek V3.2 and Kimi K2.7 Code is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Kimi K2.7 Code is priced at $0.95 input / $4.00 output per 1M tokens, versus $0.28 input / $0.42 output per 1M tokens for DeepSeek V3.2. Kimi K2.7 Code has the larger context window at 256K, compared with 128K for DeepSeek V3.2.

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 DeepSeek V3.2 and Kimi K2.7 Code
CategoryDeepSeek V3.2ΔKimi K2.7 Code
CodingDeepSeek V3.260.9MarginNo overlapKimi K2.7 CodeNot measured
MathDeepSeek V3.217.1MarginNo overlapKimi K2.7 CodeNot measured

Operational comparison

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

MetricDeepSeek V3.2Kimi K2.7 CodeComparison
Input / output priceUSD per 1M tokensDeepSeek V3.2$0.28 input / $0.42 outputKimi K2.7 Code$0.95 input / $4 outputDeepSeek V3.2 has the lower combined listed price.
Generation speedtokens per secondDeepSeek V3.235 tok/sKimi K2.7 CodeNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenDeepSeek V3.23.75 sKimi K2.7 CodeNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensDeepSeek V3.2128KKimi K2.7 Code256KKimi K2.7 Code lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
Claw-EvalSource 40.2%Not comparable
VITA-BenchSource 18.5%Not comparable
τ²-bench resultsSource 78.9%90.1%Kimi K2.7 Code leads
Gert LabsSource 29.57%Not comparable
Kimi Claw 24/7Source 46.9%Not comparable
MCP AtlasSource 76%Not comparable
MCP Mark VerifiedSource 81.1%Not comparable
AA Agentic IndexSource 29.6%Not comparable
GDPval-AASource 34.3%Not comparable
GDPval-AASource 1187Not comparable
Coding
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
SWE-RebenchSource 60.9%Not comparable
React Native EvalsSource 71.5%Not comparable
AA-SciCodeSource 38.7%47.5%Kimi K2.7 Code leads
Kimi Code Bench v2Source 62.0%Not comparable
ProgramBenchSource 53.6%Not comparable
MLS-Bench LiteSource 35.1%Not comparable
cursorBench32Source 49.7%Not comparable
AA Coding IndexSource 60.8%Not comparable
Reasoning
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
AA-LCRSource 39.0%66.3%Kimi K2.7 Code leads
CritPtSource 0.9%10.0%Kimi K2.7 Code leads
Knowledge
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
Artificial Analysis Intelligence IndexSource 24.7%42.0%Kimi K2.7 Code leads
AA-GPQA DiamondSource 75.1%89.6%Kimi K2.7 Code leads
AA-HLESource 10.5%32.8%Kimi K2.7 Code leads
AA-Omniscience IndexSource -46.7%-10.7%Kimi K2.7 Code leads
AA-Omniscience AccuracySource 24.2%38.6%Kimi K2.7 Code leads
AA-Omniscience Hallucination RateSource 93.5%80.3%Kimi K2.7 Code leads
Math
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
FrontierMath v2 (Tiers 1-3)Source 22.100%Not comparable
FrontierMath v2 (Tier 4)Source 2.100%Not comparable
Multimodal
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
Design Arena WebsiteSource 12041302Kimi K2.7 Code leads
Inst. Following
BenchmarkDeepSeek V3.2Kimi K2.7 CodeResult
AA-IFBenchSource 49.0%63.1%Kimi K2.7 Code leads
Frequently Asked Questions (3)

Can I compare DeepSeek V3.2 and Kimi K2.7 Code on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for DeepSeek V3.2 and Kimi K2.7 Code today?

DeepSeek V3.2: $0.28 input / $0.42 output per 1M tokens Kimi K2.7 Code: $0.95 input / $4.00 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

Self-host vs API cost

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

DeepSeek V3.2
API / mo$525
Self-host / moNot listed
Break-even
Proprietary model — self-hosting not applicable.
Kimi K2.7 Code
API / mo$3,713
Self-host / mo$18,221
Break-even326M/day
Model the full break-even

Related Comparisons

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.