Mistral Large vs Mistral Small 3
Mistral Small 3 leads Mistral Large on the Artificial Analysis Intelligence Index, 6.7 to 5.8, and Mistral Small 3 costs 75.0x less per output token ($0.08 vs $6.00 per million). Updated October 21, 2026; 31 benchmarks have a result for both.
Mistral Large or Mistral Small 3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mistral Large for a larger context window (128K against 33K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 31
- Mistral Large only
- 13
- Mistral Small 3 only
- 5
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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 Small 3
Mistral Small 3 leads, 6.7 against 5.8.
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
Mistral Large
Mistral Large takes 128K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 3
Mistral Large $0.0050, Mistral Small 3 $0.0001 per turn.
List prices
At a glance
- Coding index
- Mistral Large not benchmarked, Mistral Small 3 not benchmarked.
- Widest category
- Knowledge, 7.8 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena Text: French: Mistral Large 1325 against Mistral Small 3 1204, 20.3 points apart on a 0 to 100 scale.
- Output price
- Mistral Large $6.00 against Mistral Small 3 $0.08 per million output tokens, 75.0x apart.
- Context window
- Mistral Large takes 128K tokens, Mistral Small 3 33K.
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 | Mistral Large | Bars | Mistral Small 3 | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 3 | 2 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 1 | ||
| General | 15 | 0 | ||
| All shared boards | 26 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | 37.1% | Not measured | Only Mistral Large measured |
| LiveCodeBench (Artificial Analysis run) | 17.8% | 25.2% | Mistral Small 3 |
| LMArena Text: coding | 1275 | 1246 | Mistral Large |
| LMArena Text: software and IT | 1274 | 1248 | Mistral Large |
| Neither model has a result on the other 34 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.8 | 6.7 | Mistral Small 3 |
| Epoch Capabilities Index | 122.1 | Not measured | Only Mistral Large measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 19.6% | Only Mistral Small 3 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| GPQA Diamond | 47.7% | Not measured | Only Mistral Large measured |
| GPQA Diamond (Artificial Analysis run) | 35.1% | 46.2% | Mistral Small 3 |
| Humanity's Last Exam (Artificial Analysis run) | 3.5% | 3.8% | Mistral Small 3 |
| LMArena Text: hard prompts | 1257 | 1233 | Mistral Large |
| LMArena Text: expert | 1208 | 1202 | Mistral Large |
| LMArena Text: hard prompts in English | 1268 | 1243 | Mistral Large |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| AIME | 9.2% | Not measured | Only Mistral Large measured |
| MATH 500 (Vals AI) | 74.4% | Not measured | Only Mistral Large measured |
| MGSM (Vals AI) | 87.2% | Not measured | Only Mistral Large measured |
| AA Math Index | Not measured | 4.3 | Only Mistral Small 3 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 4.3% | Only Mistral Small 3 measured |
| LMArena Text: math | 1261 | 1240 | Mistral Large |
| LMArena Text: mathematical work | 1257 | 1243 | Mistral Large |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| MMLU Pro | 69.7% | Not measured | Only Mistral Large measured |
| TaxEval (Vals AI) | 63.8% | Not measured | Only Mistral Large measured |
| MedQA (Vals AI) | 76.2% | Not measured | Only Mistral Large measured |
| MMLU Pro (Artificial Analysis run) | 51.5% | 65.2% | Mistral Small 3 |
| MMLU | 68.8% | Not measured | Only Mistral Large measured |
| LMArena Text: science | 1260 | 1235 | Mistral Large |
| LMArena Text: medicine and healthcare | 1255 | 1215 | Mistral Large |
| LMArena Text: legal and government | 1275 | 1219 | Mistral Large |
| LMArena Text: business and finance | 1238 | 1205 | Mistral Large |
| 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 | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index150
| Benchmark | Mistral Large | Mistral Small 3 | Leader |
|---|---|---|---|
| IFBench | Not measured | 26.4% | Only Mistral Small 3 measured |
| Long context reasoning (AA-LCR) | Not measured | 0.0% | Only Mistral Small 3 measured |
| DTBench | 60.8% | Not measured | Only Mistral Large measured |
| LMArena Text | 1265 | 1234 | Mistral Large |
| LMArena Text: instruction following | 1249 | 1214 | Mistral Large |
| LMArena Text: creative writing | 1242 | 1194 | Mistral Large |
| LMArena Text: English | 1284 | 1256 | Mistral Large |
| LMArena Text: non-English | 1235 | 1198 | Mistral Large |
| LMArena Text: Chinese | 1239 | 1204 | Mistral Large |
| LMArena Text: German | 1242 | 1211 | Mistral Large |
| LMArena Text: Japanese | 1170 | 1111 | Mistral Large |
| LMArena Text: Korean | 1202 | 1188 | Mistral Large |
| LMArena Text: French | 1325 | 1204 | Mistral Large |
| LMArena Text: Spanish | 1268 | Not measured | Only Mistral Large measured |
| LMArena Text: Russian | 1252 | 1216 | Mistral Large |
| LMArena Text: Polish | 1157 | Not measured | Only Mistral Large measured |
| LMArena Text: multi-turn | 1260 | 1217 | Mistral Large |
| LMArena Text: longer queries | 1261 | 1246 | Mistral Large |
| LMArena Text: writing and language | 1261 | 1214 | Mistral Large |
| LMArena Text: entertainment and media | 1230 | 1184 | Mistral Large |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Large | Mistral Small 3 | 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
Mistral Small 3 costs less
Repository review
50K input + 3K output tokens
Mistral Small 3 costs less
Agent loop
200K input + 10K output tokens
Mistral Small 3 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 | Mistral Large | Mistral Small 3 |
|---|---|---|
| Maker | Mistral AI | Mistral AI |
| Weights | No public weights listed | Open weights |
| Released | February 26, 2024 | January 30, 2025 |
| Context window | 128K | 33K |
| Input $/Mtok | $2.00 | $0.05 |
| Output $/Mtok | $6.00 | $0.08 |
| 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 Mistral Large better than Mistral Small 3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mistral Large for a larger context window (128K against 33K tokens) and work measured by LiveCodeBench (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Mistral Large or Mistral Small 3?
Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens; Mistral Small 3 costs $0.05 and $0.08. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Large or Mistral Small 3?
Mistral Large, with 128K tokens against 33K.
How many benchmarks is the Mistral Large vs Mistral Small 3 comparison based on?
31 benchmarks have a result for both models as of October 21, 2026. Mistral Large's coding index rests on 0 independent benchmarks and Mistral Small 3's on 0. Where only one model has a result, the page says so instead of naming a winner.