Compare / Gemma 3 4B vs Mistral Large 2 (2407)

Gemma 3 4B vs Mistral Large 2 (2407)

Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.

GoogleGemma 3 4B Released 11 Mar 2025 · $0.040 in · $0.050 out
Mistral AIMistral Large 2 (2407) Released 24 Jul 2024 · $2.00 in · $6.00 out
Gemma 3 4B wins 44 too close to callMistral Large 2 (2407) wins 7

Of the 15 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331). See also Google vs Mistral AI, every model from both labs.

Gemma 3 4B or Mistral Large 2 (2407)? The short answer

Pick Mistral Large 2 (2407) if quality matters most: it scores higher (Intelligence Index 6.8 against 4.8). Pick Gemma 3 4B if cost matters more: it costs 71 times less per token.

  • Gemma 3 4B is cheaper: $0.042 against $3.00 per million tokens, 71 times less.
  • Mistral Large 2 (2407) scores higher on the Artificial Analysis Intelligence Index: 6.8 against 4.8.
  • Gemma 3 4B is newer: released 11 Mar 2025, against 24 Jul 2024 for Mistral Large 2 (2407).
  • On third-party benchmarks, on the results both models have: Mistral Large 2 (2407) does better for reasoning and knowledge and writing.

Head to head

4.8
Intelligence Index
6.8
$0.042
Price per million tokens, blendedlower is better
$3.00
131,072
Context window, tokens
131,072

Every fact side by side

Gemma 3 4BMistral Large 2 (2407)
Price per million tokens$0.040 in · $0.050 out$2.00 in · $6.00 out
Blended (3 in : 1 out)$0.042$3.00
Cheapest host, blended$0.042 (Parasail, BF16)$3.00 (Mistral)
Intelligence Index4.86.8
Spring Prompt overall––
Output speed, tokens a second––
Context window131,072 tokens131,072 tokens
Released11 Mar 2025 (newer)24 Jul 2024
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 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 181 of 187 183 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 157 of 169 127 of 169
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 4BMistral Large 2 (2407)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 255 · 240 of 387 measured 1,303 1,314
Business, management and finance · TextArena rating, higher is better 208 · 256 of 380 measured 1,330 1,290
Creative writing · TextArena rating, higher is better 243 · 226 of 385 measured 1,275 1,287
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 246 · 224 of 249 measured 4.8 6.8
GPQA Diamond% of questions, higher is better 227 · 208 of 232 measured 29.1% 47.2%
Humanity's Last Exam% of questions, higher is better 194 · 245 of 250 measured 5.3% 2.9%
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 185 · 107 of 230 measured 24.0 40.9
Requested-length error · UGI% off the requested word count, lower is better 33 · 49 of 230 measured 9.0% 11.0%
Style adherence · UGIscore from 0 to 1, higher is better 214 · 60 of 230 measured 0.29 0.36
Show all 15 results (6 more)
MeasureGemma 3 4BMistral Large 2 (2407)
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 270 · 233 of 338 measured 1,260 1,302
Instruction following · TextArena rating, higher is better 270 · 236 of 387 measured 1,267 1,300
Writing, literature and language · TextArena rating, higher is better 237 · 226 of 386 measured 1,298 1,303
Artificial Analysis reported by Artificial Analysis · 3 results
IFBench% of instructions, higher is better 187 · 175 of 195 measured 28.3% 31.6%
Long-context reasoning (AA-LCR)% of questions, higher is better 226 · 229 of 241 measured 6.7% 2.0%
τ²-bench telecom% of tasks, higher is better 187 · 128 of 193 measured 5.0% 33.0%

Quick answers

Is Gemma 3 4B better than Mistral Large 2 (2407)?

Pick Mistral Large 2 (2407) if quality matters most: it scores higher (Intelligence Index 6.8 against 4.8). Pick Gemma 3 4B if cost matters more: it costs 71 times less per token.

Which is cheaper, Gemma 3 4B or Mistral Large 2 (2407)?

Gemma 3 4B is cheaper: $0.042 against $3.00 per million tokens, 71 times less.

Which is better for reasoning and knowledge, Gemma 3 4B or Mistral Large 2 (2407)?

Gemma 3 4B ranks 181 of 187 models on sale for hard questions across science, maths and general knowledge, against 183 for Mistral Large 2 (2407).

Which is better for writing, Gemma 3 4B or Mistral Large 2 (2407)?

Mistral Large 2 (2407) ranks 127 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 Mistral Large 2 (2407) 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.