Mistral Large vs Mistral Small 3.2 24B
Mistral Small 3.2 24B costs 20.0x less per output token than Mistral Large ($0.30 vs $6.00 per million). Updated October 21, 2026; no benchmark has tested both models yet.
- Coding
- No data
- Overall
- 5.8
- Output $/M
- $6.00
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.30
Mistral Large or Mistral Small 3.2 24B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
No benchmark has tested both yet. Mistral Large has results on LiveCodeBench (Vals AI), LiveCodeBench (Artificial Analysis run) and LMArena Text: coding; Mistral Small 3.2 24B on Design Arena: websites, Design Arena: UI components and Design Arena: game dev. Compare them on price and context instead.
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
No call
Only Mistral Large has a AA Intelligence Index result, 5.8.
Directional only
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
Web design
Design Arena: websites
No call
Only Mistral Small 3.2 24B has a Design Arena: websites result, 896.
Directional only
Long documents
Listed context window
Mistral Small 3.2 24B
Mistral Small 3.2 24B takes 256K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 3.2 24B
Mistral Large $0.0050, Mistral Small 3.2 24B $0.0003 per turn.
List prices
At a glance
- Coding index
- Mistral Large not benchmarked, Mistral Small 3.2 24B not benchmarked.
- Widest category
- None yet: no category has been tested on both models.
- Widest single gap
- None yet: no benchmark has tested both models.
- Output price
- Mistral Large $6.00 against Mistral Small 3.2 24B $0.30 per million output tokens, 20.0x apart.
- Context window
- Mistral Large takes 128K tokens, Mistral Small 3.2 24B 256K.
Benchmark by benchmark
Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | 37.1% | Not measured | Only Mistral Large measured |
| LiveCodeBench (Artificial Analysis run) | 17.8% | Not measured | Only Mistral Large measured |
| LMArena Text: coding | 1275 | Not measured | Only Mistral Large measured |
| LMArena Text: software and IT | 1274 | Not measured | Only Mistral Large measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.8 | Not measured | Only Mistral Large measured |
| Epoch Capabilities Index | 122.1 | Not measured | Only Mistral Large measured |
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | Leader |
|---|---|---|---|
| GPQA Diamond | 47.7% | Not measured | Only Mistral Large measured |
| GPQA Diamond (Artificial Analysis run) | 35.1% | Not measured | Only Mistral Large measured |
| Humanity's Last Exam (Artificial Analysis run) | 3.5% | Not measured | Only Mistral Large measured |
| LMArena Text: hard prompts | 1257 | Not measured | Only Mistral Large measured |
| LMArena Text: expert | 1208 | Not measured | Only Mistral Large measured |
| LMArena Text: hard prompts in English | 1268 | Not measured | Only Mistral Large measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | 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 |
| LMArena Text: math | 1261 | Not measured | Only Mistral Large measured |
| LMArena Text: mathematical work | 1257 | Not measured | Only Mistral Large measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index9 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | 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% | Not measured | Only Mistral Large measured |
| MMLU | 68.8% | Not measured | Only Mistral Large measured |
| LMArena Text: science | 1260 | Not measured | Only Mistral Large measured |
| LMArena Text: medicine and healthcare | 1255 | Not measured | Only Mistral Large measured |
| LMArena Text: legal and government | 1275 | Not measured | Only Mistral Large measured |
| LMArena Text: business and finance | 1238 | Not measured | Only Mistral Large measured |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 896 | Only Mistral Small 3.2 24B measured |
| Design Arena: UI components | Not measured | 907 | Only Mistral Small 3.2 24B measured |
| Design Arena: game dev | Not measured | 888 | Only Mistral Small 3.2 24B measured |
| Design Arena: data viz | Not measured | 929 | Only Mistral Small 3.2 24B measured |
| Design Arena: all code categories | Not measured | 907 | Only Mistral Small 3.2 24B measured |
| Neither model has a result on the other 4 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index18 boards measured
| Benchmark | Mistral Large | Mistral Small 3.2 24B | Leader |
|---|---|---|---|
| DTBench | 60.8% | Not measured | Only Mistral Large measured |
| LMArena Text | 1265 | Not measured | Only Mistral Large measured |
| LMArena Text: instruction following | 1249 | Not measured | Only Mistral Large measured |
| LMArena Text: creative writing | 1242 | Not measured | Only Mistral Large measured |
| LMArena Text: English | 1284 | Not measured | Only Mistral Large measured |
| LMArena Text: non-English | 1235 | Not measured | Only Mistral Large measured |
| LMArena Text: Chinese | 1239 | Not measured | Only Mistral Large measured |
| LMArena Text: German | 1242 | Not measured | Only Mistral Large measured |
| LMArena Text: Japanese | 1170 | Not measured | Only Mistral Large measured |
| LMArena Text: Korean | 1202 | Not measured | Only Mistral Large measured |
| LMArena Text: French | 1325 | Not measured | Only Mistral Large measured |
| LMArena Text: Spanish | 1268 | Not measured | Only Mistral Large measured |
| LMArena Text: Russian | 1252 | Not measured | Only Mistral Large measured |
| LMArena Text: Polish | 1157 | Not measured | Only Mistral Large measured |
| LMArena Text: multi-turn | 1260 | Not measured | Only Mistral Large measured |
| LMArena Text: longer queries | 1261 | Not measured | Only Mistral Large measured |
| LMArena Text: writing and language | 1261 | Not measured | Only Mistral Large measured |
| LMArena Text: entertainment and media | 1230 | Not measured | Only Mistral Large measured |
| Neither model has a result on the other 28 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 3.2 24B costs less
Repository review
50K input + 3K output tokens
Mistral Small 3.2 24B costs less
Agent loop
200K input + 10K output tokens
Mistral Small 3.2 24B 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 3.2 24B |
|---|---|---|
| Maker | Mistral AI | Mistral AI |
| Weights | No public weights listed | Open weights |
| Released | February 26, 2024 | June 20, 2025 |
| Context window | 128K | 256K |
| Input $/Mtok | $2.00 | $0.10 |
| Output $/Mtok | $6.00 | $0.30 |
| 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 3.2 24B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, Mistral Large or Mistral Small 3.2 24B?
Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens; Mistral Small 3.2 24B costs $0.10 and $0.30. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Large or Mistral Small 3.2 24B?
Mistral Small 3.2 24B, with 256K tokens against 128K.
Has any benchmark tested both Mistral Large and Mistral Small 3.2 24B?
No benchmark has tested both yet. Mistral Large has results on LiveCodeBench (Vals AI), LiveCodeBench (Artificial Analysis run) and LMArena Text: coding; Mistral Small 3.2 24B on Design Arena: websites, Design Arena: UI components and Design Arena: game dev. Compare them on price and context instead. Data as of October 21, 2026.