Skip to content
ModelCap

Head-to-head comparison

Gemma 4 31B vs Kimi K3

Gemma 4 31B (Google) and Kimi K3 (Moonshot AI) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 22 September 2026

As of 22 September 2026, Kimi K3 holds the stronger ModelCap Index position (#12 vs #29); Gemma 4 31B is 44.1× cheaper per output token ($0.34/1M vs $15.00/1M); Kimi K3 offers the longer context window (1M vs 262K tokens); and Gemma 4 31B ships open weights.

Which should you choose?

Choose Gemma 4 31B if…

  • API cost matters — $0.34/1M output tokens against $15.00/1M, about 44.1× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.09/1M against $3.00/1M.
  • you want to self-host: Gemma 4 31B ships open weights while Kimi K3 is restricted license.

Choose Kimi K3 if…

  • you want the stronger overall ModelCap Index position — #12 against #29 (84.0 vs 73.8 points).
  • you need the longer context window — 1M tokens against 262K.
  • you want provider choice — 17 listed API providers against 11.
  • Arena coding is your yardstick — 1538 against 1499.
  • AA Humanity's Last Exam is your yardstick — 46.9% against 11.8%.
  • WildClawBench OpenClaw is your yardstick — 54.5 against 37.6.
  • you want the more recently listed model — Kimi K3 was listed 16 July 2026, Gemma 4 31B 2 April 2026.

Gemma 4 31B vs Kimi K3: specs, pricing and context

Specification comparison of Gemma 4 31B and Kimi K3
FieldGemma 4 31BGoogleKimi K3Moonshot AI
ModelCap Index position#29#12
Index score73.884.0
EvidenceMeasuredMeasured
Input price / 1M tokens$0.09$3.00
Output price / 1M tokens$0.34$15.00
Context window262K tokens1M tokens
Max output tokens16K944K
API providers listed1117
Weight accessOpen weightsRestricted license
Input modalitiesImage, Text, VideoText, Image, Video
First listed2 April 202616 July 2026
PublisherGoogleMoonshot AI

Evidence: 3 public benchmark observations across 3 boards · 6 public benchmark observations across 6 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Gemma 4 31B vs Kimi K3

Public benchmark boards where Gemma 4 31B or Kimi K3 has a published result
BoardGemma 4 31BKimi K3Leads
Arena codingArena (LMArena)14991483–151415381530–1547MaxKimi K3
LMArena AgentLMArena—6.2%5.6%–6.8%MaxOnly one result
ARC-AGI-2ARC Prize Foundation—60.4%MaxOnly one result
AA Intelligence IndexArtificial Analysis—43.6intelligence-index:v4.3:maxOnly one result
AA τ²-Bench TelecomArtificial Analysis65.5%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Gemma 4 31B (Non-reasoning)":reasoning=false—Only one result
AA Humanity's Last ExamArtificial Analysis11.8%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemma 4 31B (Non-reasoning)":reasoning=false46.9%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Kimi K3 (max)":reasoning=trueKimi K3
WildClawBench OpenClawWildClawBench37.654.5Kimi K3

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Gemma 4 31B vs Kimi K3: common questions

Is Gemma 4 31B better than Kimi K3?

Kimi K3 ranks higher on the ModelCap Index as of 22 September 2026: #12 against #29. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Gemma 4 31B cheaper than Kimi K3?

Gemma 4 31B is cheaper on output tokens: $0.34/1M against $15.00/1M. Input tokens are $0.09/1M for Gemma 4 31B and $3.00/1M for Kimi K3. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.35 for Gemma 4 31B versus $13.50 for Kimi K3. Gemma 4 31B costs 97.4% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Gemma 4 31B or Kimi K3?

Kimi K3 has the larger context window: 1M tokens against 262K.

Which is better for coding, Gemma 4 31B or Kimi K3?

Arena coding: Gemma 4 31B 1499, Kimi K3 1538 — Kimi K3 leads.

Are Gemma 4 31B and Kimi K3 open-weight models?

Gemma 4 31B: Open weights. Kimi K3: Restricted license. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Gemma 4 31B and Kimi K3?

ModelCap currently lists 11 API providers for Gemma 4 31B and 17 for Kimi K3, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Gemma 4 31B vs Kimi K3 comparison?

Every figure comes from the sealed ModelCap dataset published 22 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further