Skip to main content

Model comparison

Gemma 4 31B vs Kimi K2.7 Code

Data verified

Head-to-head evidence from 15 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

60.19/100
Margin
6.2pts
← winning
Moonshot AI
54.03/100
0 category wins0 category wins

Public leaderboard positions: Gemma 4 31B #47 (Supported); Kimi K2.7 Code #92 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemma 4 31B and Kimi K2.7 Code share 15 comparable benchmark results. 0 of 8 categories are comparable. 15 results are unique to Gemma 4 31B; 8 to Kimi K2.7 Code.

Updated July 27, 2026
Shared results
15
Gemma 4 31B only
15
Kimi K2.7 Code only
8
Comparable categories
0 / 8

Benchmark data for Gemma 4 31B and Kimi K2.7 Code is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 5 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 $0.00 input / $0.00 output per 1M tokens for Gemma 4 31B.

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 Gemma 4 31B and Kimi K2.7 Code
CategoryGemma 4 31BΔKimi K2.7 Code
CodingGemma 4 31B41.6MarginNo overlapKimi K2.7 CodeNot measured
KnowledgeGemma 4 31B52.9MarginNo overlapKimi K2.7 CodeNot measured
MultimodalGemma 4 31B76.9MarginNo overlapKimi K2.7 CodeNot measured

Operational comparison

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

MetricGemma 4 31BKimi K2.7 CodeComparison
Input / output priceUSD per 1M tokensGemma 4 31B$0 input / $0 outputKimi K2.7 Code$0.95 input / $4 outputGemma 4 31B has the lower combined listed price.
Generation speedtokens per secondGemma 4 31BNot availableKimi K2.7 CodeNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemma 4 31BNot availableKimi K2.7 CodeNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemma 4 31B256KKimi K2.7 Code256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemma 4 31BKimi K2.7 CodeResult
AA Agentic IndexSource 14.4%29.6%Kimi K2.7 Code leads
τ²-bench resultsSource 59.9%90.1%Kimi K2.7 Code leads
GDPval-AASource 15.5%34.3%Kimi K2.7 Code leads
GDPval-AASource 8111186Kimi K2.7 Code leads
Gert LabsSource 35.26%Not comparable
AA EnterpriseOps-GymSource 28.3%Not comparable
AA ITBenchSource 37.3%Not comparable
terminalBenchHardSource 36.4%Not comparable
AA Harvey LABSource 47.2%Not comparable
AA Tau3 BankingSource 15.1%Not comparable
Kimi Claw 24/7Source 46.9%Not comparable
MCP AtlasSource 76%Not comparable
MCP Mark VerifiedSource 81.1%Not comparable
Coding
BenchmarkGemma 4 31BKimi K2.7 CodeResult
SWE-RebenchSource 41.6%Not comparable
React Native EvalsSource 75.2%Not comparable
AA Coding IndexSource 43.4%60.8%Kimi K2.7 Code leads
AA-SciCodeSource 43.4%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
Reasoning
BenchmarkGemma 4 31BKimi K2.7 CodeResult
AA-LCRSource 62.0%66.3%Kimi K2.7 Code leads
CritPtSource 1.4%10.0%Kimi K2.7 Code leads
Knowledge
BenchmarkGemma 4 31BKimi K2.7 CodeResult
GPQASource 84.3%Not comparable
MMLU-ProSource 85.2%Not comparable
HLESource 26.5%Not comparable
HLE w/o toolsSource 19.5%Not comparable
Artificial Analysis Intelligence IndexSource 29.4%42.0%Kimi K2.7 Code leads
AA-GPQA DiamondSource 85.7%89.6%Kimi K2.7 Code leads
AA-HLESource 22.7%32.8%Kimi K2.7 Code leads
AA-Omniscience IndexSource -45.4%-10.7%Kimi K2.7 Code leads
AA-Omniscience AccuracySource 19.9%38.6%Kimi K2.7 Code leads
AA-Omniscience Hallucination RateSource 81.6%80.3%Kimi K2.7 Code leads
AA Openness IndexSource 38.9%Not comparable
Multimodal
BenchmarkGemma 4 31BKimi K2.7 CodeResult
MMMU-ProSource 76.9%Not comparable
AA-MMMU-ProSource 73.4%Not comparable
Design Arena WebsiteSource 1300Not comparable
Inst. Following
BenchmarkGemma 4 31BKimi K2.7 CodeResult
AA-IFBenchSource 75.6%63.1%Gemma 4 31B leads
Frequently Asked Questions (3)

Can I compare Gemma 4 31B 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 Gemma 4 31B and Kimi K2.7 Code today?

Gemma 4 31B: $0.00 input / $0.00 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.

Gemma 4 31B
API / mo$0
Self-host / mo$429
Break-even
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 27, 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

One email each week. Unsubscribe anytime.