Compare / Gemma 3 4B vs Mistral Small 3

Gemma 3 4B vs Mistral Small 3

Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 4 sources that measured both models.

GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Mistral AIMistral Small 3 Released 30 Jan 2025 · $0.050 in · $0.080 out
Gemma 3 4B wins 72 too close to callMistral Small 3 wins 8

Of the 17 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 Mistral Small 3? The short answer

They score about the same, so pick Gemma 3 4B: it costs 26% less per token.

  • Gemma 3 4B is cheaper: $0.042 against $0.058 per million tokens, 26% less.
  • Mistral Small 3 scores higher on the Artificial Analysis Intelligence Index: 6.7 against 4.8.
  • Gemma 3 4B is newer: released 11 Mar 2025, against 30 Jan 2025 for Mistral Small 3.
  • On third-party benchmarks, on the results both models have: Mistral Small 3 does better for reasoning and knowledge and sticking to the facts.

Head to head

4.8
Intelligence Index
6.7
$0.042
Price per million tokens, blendedlower is better
$0.058
131,072
Context window, tokens
32,768

Every fact side by side

Gemma 3 4BMistral Small 3
Price per million tokens$0.040 in · $0.050 out$0.050 in · $0.080 out
Blended (3 in : 1 out)$0.042$0.058
Cheapest host, blended$0.042 (Parasail, BF16)–
Intelligence Index4.86.7
Spring Prompt overall––
Output speed, tokens a second––
Context window131,072 tokens32,768 tokens
Released11 Mar 2025 (newer)30 Jan 2025
WeightsOpenOpen
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 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 181 of 187 179 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 157 of 169 142 of 169
Sticking to the factsSummarising without inventing things, and factual answers 32 of 139 8 of 139

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 4BMistral Small 3
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 255 · 279 of 387 measured 1,303 1,274
Business, management and finance · TextArena rating, higher is better 208 · 280 of 380 measured 1,330 1,259
Creative writing · TextArena rating, higher is better 243 · 281 of 385 measured 1,275 1,227
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 246 · 225 of 249 measured 4.8 6.7
GPQA Diamond% of questions, higher is better 227 · 210 of 232 measured 29.1% 46.2%
Humanity's Last Exam% of questions, higher is better 194 · 229 of 250 measured 5.3% 3.8%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 185 · 131 of 230 measured 24.0 33.9
Requested-length error · UGI% off the requested word count, lower is better 33 · 25 of 230 measured 9.0% 8.0%
Style adherence · UGIscore from 0 to 1, higher is better 214 · 103 of 230 measured 0.29 0.35
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 28 · 10 of 104 measured 6.4% 5.1%
Answer rate · Vectara% of documents, higher is better 103 · 79 of 104 measured 67.3% 97.9%
Show all 17 results (6 more)
MeasureGemma 3 4BMistral Small 3
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 270 · 271 of 338 measured 1,260 1,259
Instruction following · TextArena rating, higher is better 270 · 279 of 387 measured 1,267 1,255
Writing, literature and language · TextArena rating, higher is better 237 · 282 of 386 measured 1,298 1,248
Artificial Analysis reported by Artificial Analysis · 3 results
IFBench% of instructions, higher is better 187 · 190 of 195 measured 28.3% 26.4%
Long-context reasoning (AA-LCR)% of questions, higher is better 226 · 230 of 241 measured 6.7% 0.0%
τ²-bench telecom% of tasks, higher is better 187 · 168 of 193 measured 5.0% 19.6%

Quick answers

Is Gemma 3 4B better than Mistral Small 3?

They score about the same, so pick Gemma 3 4B: it costs 26% less per token.

Which is cheaper, Gemma 3 4B or Mistral Small 3?

Gemma 3 4B is cheaper: $0.042 against $0.058 per million tokens, 26% less.

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

Mistral Small 3 ranks 179 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 Mistral Small 3?

Mistral Small 3 ranks 142 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 157 for Gemma 3 4B.

Which is better for sticking to the facts, Gemma 3 4B or Mistral Small 3?

Mistral Small 3 ranks 8 of 139 models on sale for summarising without inventing things, and factual answers, against 32 for Gemma 3 4B.

Which has the bigger context window, Gemma 3 4B or Mistral Small 3?

Gemma 3 4B: 131,072 tokens, against 32,768 for Mistral Small 3.

Run Gemma 3 4B and Mistral Small 3 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.