Compare / Gemma 3 4B vs Magistral Small 1.2

Gemma 3 4B vs Magistral Small 1.2

Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 2 sources that measured both models.

GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Mistral AIMagistral Small 1.2 Released 17 Sep 2025 · Not on sale
Gemma 3 4B wins 1Magistral Small 1.2 wins 12

Of the 13 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 Mistral AI, every model from both labs.

Gemma 3 4B or Magistral Small 1.2? The short answer

Pick Magistral Small 1.2: it scores higher (Intelligence Index 8.6 against 4.8) at about the same price.

  • Magistral Small 1.2 scores higher on the Artificial Analysis Intelligence Index: 8.6 against 4.8.
  • Magistral Small 1.2 is newer: released 17 Sep 2025, against 11 Mar 2025 for Gemma 3 4B.
  • On third-party benchmarks, on the results both models have: Magistral Small 1.2 does better for agents and tool use, reasoning and knowledge and writing.

Head to head

4.8
Intelligence Index
8.6

Every fact side by side

Gemma 3 4BMagistral Small 1.2
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 Index4.88.6
Spring Prompt overall––
Output speed, tokens a second–76
Context window131,072 tokens–
Released11 Mar 202517 Sep 2025 (newer)
WeightsOpenClosed
Developer based inthe USFrance

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 159 154 of 160
Reasoning and knowledgeHard questions across science, maths and general knowledge 181 of 187 142 of 188
WritingWhat people prefer in blind comparisons, and judged writing quality 157 of 169 125 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 4BMagistral Small 1.2
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 246 · 194 of 249 measured 4.8 8.6
GPQA Diamond% of questions, higher is better 227 · 172 of 232 measured 29.1% 66.3%
Humanity's Last Exam% of questions, higher is better 194 · 186 of 250 measured 5.3% 6.4%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 185 · 130 of 230 measured 24.0 34.0
Requested-length error · UGI% off the requested word count, lower is better 33 · 83 of 230 measured 9.0% 17.0%
Style adherence · UGIscore from 0 to 1, higher is better 214 · 126 of 230 measured 0.29 0.34
Show all 13 results (7 more)
MeasureGemma 3 4BMagistral Small 1.2
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 127 · 115 of 131 measured 0.4% 4.5%
τ-bench banking% of tasks, higher is better 121 · 113 of 121 measured 0.4% 4.5%
Artificial Analysis Coding Indexindex score, higher is better 129 · 111 of 130 measured 2.7 14.7
IFBench% of instructions, higher is better 187 · 116 of 195 measured 28.3% 44.4%
Long-context reasoning (AA-LCR)% of questions, higher is better 226 · 212 of 241 measured 6.7% 19.3%
Terminal-Bench Hard% of tasks, higher is better 180 · 156 of 190 measured 0.8% 4.5%
τ²-bench telecom% of tasks, higher is better 187 · 142 of 193 measured 5.0% 27.8%

Quick answers

Is Gemma 3 4B better than Magistral Small 1.2?

Pick Magistral Small 1.2: it scores higher (Intelligence Index 8.6 against 4.8) at about the same price.

Which is better for agents and tool use, Gemma 3 4B or Magistral Small 1.2?

Magistral Small 1.2 ranks 154 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 158 for Gemma 3 4B.

Which is better for reasoning and knowledge, Gemma 3 4B or Magistral Small 1.2?

Magistral Small 1.2 ranks 142 of 187 models on sale for hard questions across science, maths and general knowledge, against 181 for Gemma 3 4B.

Which is better for writing, Gemma 3 4B or Magistral Small 1.2?

Magistral Small 1.2 ranks 125 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 Magistral Small 1.2 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.