Compare / Gemma 3 4B vs Kimi Linear 48B A3B Instruct

Gemma 3 4B vs Kimi Linear 48B A3B Instruct

Which is cheaper, which is more capable, and which does better at each kind of work, from 10 results on 2 sources that measured both models.

GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Moonshot AIKimi Linear 48B A3B Instruct Released 30 Oct 2025 · Not on sale
Gemma 3 4B wins 4Kimi Linear 48B A3B Instruct wins 6

Of the 10 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Google vs Moonshot AI, every model from both labs.

Gemma 3 4B or Kimi Linear 48B A3B Instruct? The short answer

Pick Kimi Linear 48B A3B Instruct: it scores higher (Intelligence Index 7.3 against 4.8) at about the same price.

  • Kimi Linear 48B A3B Instruct scores higher on the Artificial Analysis Intelligence Index: 7.3 against 4.8.
  • Kimi Linear 48B A3B Instruct is newer: released 30 Oct 2025, against 11 Mar 2025 for Gemma 3 4B.
  • On third-party benchmarks, on the results both models have: Kimi Linear 48B A3B Instruct does better for reasoning and knowledge and writing.

Head to head

4.8
Intelligence Index
7.3

Every fact side by side

Gemma 3 4BKimi Linear 48B A3B Instruct
Price per million tokens$0.040 in · $0.050 outNot on sale
Blended (3 in : 1 out)$0.042–
Cheapest host, blended$0.042 (Parasail, BF16)–
Intelligence Index4.87.3
Spring Prompt overall––
Output speed, tokens a second––
Context window131,072 tokens–
Released11 Mar 202530 Oct 2025 (newer)
WeightsOpenClosed
Developer based inthe USChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 158 of 159 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 181 of 187 185 of 188
WritingWhat people prefer in blind comparisons, and judged writing quality 157 of 169 116 of 170
Sticking to the factsSummarising without inventing things, and factual answers 32 of 139 not measured

Every shared result

Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.

MeasureGemma 3 4BKimi Linear 48B A3B Instruct
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 246 · 213 of 249 measured 4.8 7.3
GPQA Diamond% of questions, higher is better 227 · 220 of 232 measured 29.1% 41.2%
Humanity's Last Exam% of questions, higher is better 194 · 248 of 250 measured 5.3% 2.5%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 185 · 119 of 230 measured 24.0 37.7
Requested-length error · UGI% off the requested word count, lower is better 33 · 111 of 230 measured 9.0% 20.0%
Style adherence · UGIscore from 0 to 1, higher is better 214 · 175 of 230 measured 0.29 0.32
Show all 10 results (4 more)
MeasureGemma 3 4BKimi Linear 48B A3B Instruct
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 187 · 188 of 195 measured 28.3% 28.1%
Long-context reasoning (AA-LCR)% of questions, higher is better 226 · 196 of 241 measured 6.7% 28.0%
Terminal-Bench Hard% of tasks, higher is better 180 · 125 of 190 measured 0.8% 11.4%
τ²-bench telecom% of tasks, higher is better 187 · 188 of 193 measured 5.0% 0.0%

Quick answers

Is Gemma 3 4B better than Kimi Linear 48B A3B Instruct?

Pick Kimi Linear 48B A3B Instruct: it scores higher (Intelligence Index 7.3 against 4.8) at about the same price.

Which is better for reasoning and knowledge, Gemma 3 4B or Kimi Linear 48B A3B Instruct?

Gemma 3 4B ranks 181 of 187 models on sale for hard questions across science, maths and general knowledge, against 185 for Kimi Linear 48B A3B Instruct.

Which is better for writing, Gemma 3 4B or Kimi Linear 48B A3B Instruct?

Kimi Linear 48B A3B Instruct ranks 116 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 157 for Gemma 3 4B.

Run Gemma 3 4B and Kimi Linear 48B A3B Instruct on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.