Skip to content
ModelCap

Head-to-head comparison

Gemma 4 26B A4B vs Gemma 4 31B

Gemma 4 26B A4B (Google) and Gemma 4 31B (Google) 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, Gemma 4 31B holds the stronger ModelCap Index position (#29 vs #38); and Gemma 4 26B A4B is cheaper per output token ($0.30/1M vs $0.34/1M).

Which should you choose?

Choose Gemma 4 26B A4B if…

  • API cost matters — $0.30/1M output tokens against $0.34/1M.
  • you want provider choice — 12 listed API providers against 11.
  • you want the more recently listed model — Gemma 4 26B A4B was listed 3 April 2026, Gemma 4 31B 2 April 2026.

Choose Gemma 4 31B if…

  • you want the stronger overall ModelCap Index position — #29 against #38 (73.8 vs 70.2 points).
  • Arena coding is your yardstick — 1499 against 1481.
  • AA τ²-Bench Telecom is your yardstick — 65.5% against 40.4%.
  • AA Humanity's Last Exam is your yardstick — 11.8% against 11.5%.

Gemma 4 26B A4B vs Gemma 4 31B: specs, pricing and context

Specification comparison of Gemma 4 26B A4B and Gemma 4 31B
FieldGemma 4 26B A4BGoogleGemma 4 31BGoogle
ModelCap Index position#38#29
Index score70.273.8
EvidenceMeasuredMeasured
Input price / 1M tokens$0.09$0.09
Output price / 1M tokens$0.30$0.34
Context window262K tokens262K tokens
Max output tokens236K16K
API providers listed1211
Weight accessOpen weightsOpen weights
Input modalitiesImage, Text, VideoImage, Text, Video
First listed3 April 20262 April 2026
PublisherGoogleGoogle

Evidence: 2 public benchmark observations across 2 boards · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Gemma 4 26B A4B vs Gemma 4 31B

Public benchmark boards where Gemma 4 26B A4B or Gemma 4 31B has a published result
BoardGemma 4 26B A4BGemma 4 31BLeads
Arena codingArena (LMArena)14811466–149614991483–1514Gemma 4 31B
AA τ²-Bench TelecomArtificial Analysis40.4%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Gemma 4 26B A4B (Non-reasoning)":reasoning=false65.5%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Gemma 4 31B (Non-reasoning)":reasoning=falseGemma 4 31B
AA Humanity's Last ExamArtificial Analysis11.5%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemma 4 26B A4B (Non-reasoning)":reasoning=false11.8%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemma 4 31B (Non-reasoning)":reasoning=falseGemma 4 31B
WildClawBench OpenClawWildClawBench—37.6Only one result

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 26B A4B vs Gemma 4 31B: common questions

Is Gemma 4 26B A4B better than Gemma 4 31B?

Gemma 4 31B ranks higher on the ModelCap Index as of 22 September 2026: #29 against #38. 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 26B A4B cheaper than Gemma 4 31B?

Gemma 4 26B A4B is cheaper on output tokens: $0.30/1M against $0.34/1M. Input tokens are $0.09/1M for Gemma 4 26B A4B and $0.09/1M for Gemma 4 31B. 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 $0.33 for Gemma 4 26B A4B versus $0.35 for Gemma 4 31B. Gemma 4 26B A4B costs 5.7% 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 26B A4B or Gemma 4 31B?

Both publish a 262K-token context window.

Which is better for coding, Gemma 4 26B A4B or Gemma 4 31B?

Arena coding: Gemma 4 26B A4B 1481, Gemma 4 31B 1499 — Gemma 4 31B leads.

Are Gemma 4 26B A4B and Gemma 4 31B open-weight models?

Gemma 4 26B A4B: Open weights. Gemma 4 31B: Open weights. 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 26B A4B and Gemma 4 31B?

ModelCap currently lists 12 API providers for Gemma 4 26B A4B and 11 for Gemma 4 31B, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Gemma 4 26B A4B vs Gemma 4 31B 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