Gemma 3 4B vs Mistral Large
Updated October 21, 2026. 29 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Gemma 3 4B has the edge where output tokens cost 80.0x less, and where the context window is larger, 131K against 128K tokens.
- Shared results
- 29
- Gemma 3 4B only
- 10
- Mistral Large only
- 15
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Mistral Large
Mistral Large leads, 5.8 against 4.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Mistral Large has a GPQA Diamond result, 47.7%.
Directional only
Math
AIME
No call
Only Mistral Large has a AIME result, 9.2%.
Directional only
Knowledge
MMLU Pro
No call
Only Mistral Large has a MMLU Pro result, 69.7%.
Directional only
Long documents
Listed context window
Gemma 3 4B
Gemma 3 4B takes 131K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 3 4B
Gemma 3 4B $0.0001, Mistral Large $0.0050 per turn.
List prices
At a glance
- Coding index
- Gemma 3 4B not benchmarked, Mistral Large not benchmarked.
- Widest category
- Knowledge, 10.5 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena Text: medicine and healthcare: Gemma 3 4B 1342 against Mistral Large 1255, 14.5 points apart on a 0 to 100 scale.
- Output price
- Gemma 3 4B $0.075 against Mistral Large $6.00 per million output tokens, 80.0x apart.
- Context window
- Gemma 3 4B takes 131K tokens, Mistral Large 128K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Gemma 3 4B | Bars | Mistral Large | Ties |
|---|---|---|---|---|
| Coding | 0 | 3 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 2 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 4 | 1 | ||
| General | 9 | 3 | ||
| All shared boards | 15 | 14 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| AA Coding Index | 2.7 | Not measured | Only Gemma 3 4B measured |
| LiveCodeBench (Vals AI) | Not measured | 37.1% | Only Mistral Large measured |
| LiveCodeBench (Artificial Analysis run) | 11.2% | 17.8% | Mistral Large |
| Terminal-Bench Hard (Artificial Analysis run) | 0.8% | Not measured | Only Gemma 3 4B measured |
| LMArena Text: coding | 1230 | 1275 | Mistral Large |
| LMArena Text: software and IT | 1269 | 1274 | Mistral Large |
| Neither model has a result on the other 32 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| AA Intelligence Index | 4.8 | 5.8 | Mistral Large |
| Epoch Capabilities Index | 115.9 | 122.1 | Mistral Large |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 5.0% | Not measured | Only Gemma 3 4B measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index23
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 47.7% | Only Mistral Large measured |
| GPQA Diamond (Artificial Analysis run) | 29.1% | 35.1% | Mistral Large |
| Humanity's Last Exam (Artificial Analysis run) | 5.3% | 3.5% | Gemma 3 4B |
| GPQA Diamond (Epoch AI run) | 23.2% | Not measured | Only Gemma 3 4B measured |
| LMArena Text: hard prompts | 1253 | 1257 | Mistral Large |
| LMArena Text: expert | 1223 | 1208 | Gemma 3 4B |
| LMArena Text: hard prompts in English | 1253 | 1268 | Mistral Large |
| Neither model has a result on the other 14 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| AIME | Not measured | 9.2% | Only Mistral Large measured |
| MATH 500 (Vals AI) | Not measured | 74.4% | Only Mistral Large measured |
| MGSM (Vals AI) | Not measured | 87.2% | Only Mistral Large measured |
| AA Math Index | 12.7 | Not measured | Only Gemma 3 4B measured |
| AIME 2025 (Artificial Analysis run) | 12.7% | Not measured | Only Gemma 3 4B measured |
| OTIS Mock AIME | 7.5% | Not measured | Only Gemma 3 4B measured |
| LMArena Text: math | 1239 | 1261 | Mistral Large |
| LMArena Text: mathematical work | 1256 | 1257 | Mistral Large |
| Neither model has a result on the other 5 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 69.7% | Only Mistral Large measured |
| TaxEval (Vals AI) | Not measured | 63.8% | Only Mistral Large measured |
| MedQA (Vals AI) | Not measured | 76.2% | Only Mistral Large measured |
| MMLU Pro (Artificial Analysis run) | 41.7% | 51.5% | Mistral Large |
| MMLU | Not measured | 68.8% | Only Mistral Large measured |
| LMArena Text: science | 1306 | 1260 | Gemma 3 4B |
| LMArena Text: medicine and healthcare | 1342 | 1255 | Gemma 3 4B |
| LMArena Text: legal and government | 1327 | 1275 | Gemma 3 4B |
| LMArena Text: business and finance | 1311 | 1238 | Gemma 3 4B |
| Neither model has a result on the other 8 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index93
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| IFBench | 28.3% | Not measured | Only Gemma 3 4B measured |
| Long context reasoning (AA-LCR) | 6.7% | Not measured | Only Gemma 3 4B measured |
| DTBench | 50.9% | 60.8% | Mistral Large |
| LMCA | 2.8% | Not measured | Only Gemma 3 4B measured |
| LMArena Text | 1291 | 1265 | Gemma 3 4B |
| LMArena Text: instruction following | 1239 | 1249 | Mistral Large |
| LMArena Text: creative writing | 1270 | 1242 | Gemma 3 4B |
| LMArena Text: English | 1300 | 1284 | Gemma 3 4B |
| LMArena Text: non-English | 1273 | 1235 | Gemma 3 4B |
| LMArena Text: Chinese | Not measured | 1239 | Only Mistral Large measured |
| LMArena Text: German | 1281 | 1242 | Gemma 3 4B |
| LMArena Text: Japanese | Not measured | 1170 | Only Mistral Large measured |
| LMArena Text: Korean | Not measured | 1202 | Only Mistral Large measured |
| LMArena Text: French | Not measured | 1325 | Only Mistral Large measured |
| LMArena Text: Spanish | Not measured | 1268 | Only Mistral Large measured |
| LMArena Text: Russian | 1294 | 1252 | Gemma 3 4B |
| LMArena Text: Polish | Not measured | 1157 | Only Mistral Large measured |
| LMArena Text: multi-turn | 1255 | 1260 | Mistral Large |
| LMArena Text: longer queries | 1273 | 1261 | Gemma 3 4B |
| LMArena Text: writing and language | 1288 | 1261 | Gemma 3 4B |
| LMArena Text: entertainment and media | 1233 | 1230 | Gemma 3 4B |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 3 4B | Mistral Large | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 3 4B costs less
Repository review
50K input + 3K output tokens
Gemma 3 4B costs less
Agent loop
200K input + 10K output tokens
Gemma 3 4B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Google Gemma 3 4B | Mistral Large |
|---|---|---|
| Maker | Mistral AI | |
| Weights | Open weights | No public weights listed |
| Released | March 13, 2025 | February 26, 2024 |
| Context window | 131K | 128K |
| Input $/Mtok | $0.045 | $2.00 |
| Output $/Mtok | $0.075 | $6.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 3 4B better than Mistral Large for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Gemma 3 4B has the edge where output tokens cost 80.0x less, and where the context window is larger, 131K against 128K tokens.
Which is cheaper, Gemma 3 4B or Mistral Large?
Gemma 3 4B costs $0.045 per million input tokens and $0.075 per million output tokens; Mistral Large costs $2.00 and $6.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 3 4B or Mistral Large?
Gemma 3 4B, with 131K tokens against 128K.
How many benchmarks is the Gemma 3 4B vs Mistral Large comparison based on?
29 benchmarks have a result for both models as of October 21, 2026. Gemma 3 4B's coding index rests on 0 independent benchmarks and Mistral Large's on 0. Where only one model has a result, the page says so instead of naming a winner.