Mistral Small 3.1 24B vs Sonar Pro
Updated October 21, 2026. 0 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
- Coding
- No data
- Overall
- No data
- Output $/M
- $0.555
- Coding
- No data
- Overall
- 7.6
- Output $/M
- $15.00
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Mistral Small 3.1 24B has the edge where output tokens cost 27.0x less.
- Shared results
- 0
- Mistral Small 3.1 24B only
- 38
- Sonar Pro only
- 5
- Like-for-like categories
- 0 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
No call
Only Sonar Pro has a AA Intelligence Index result, 7.6.
Directional only
Long documents
Listed context window
Sonar Pro
Sonar Pro takes 200K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mistral Small 3.1 24B
Mistral Small 3.1 24B $0.0006, Sonar Pro $0.011 per turn.
List prices
At a glance
- Coding index
- Mistral Small 3.1 24B not benchmarked, Sonar Pro not benchmarked.
- Widest category
- No category has a result for both models.
- Widest single gap
- No benchmark has a result for both models.
- Output price
- Mistral Small 3.1 24B $0.555 against Sonar Pro $15.00 per million output tokens, 27.0x apart.
- Context window
- Mistral Small 3.1 24B takes 128K tokens, Sonar Pro 200K.
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.
CodingDirectional onlySix of these boards feed the Vibe Coding Index3 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| LiveCodeBench (Artificial Analysis run) | Not measured | 27.5% | Only Sonar Pro measured |
| LMArena Text: coding | 1309 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: software and IT | 1301 | Not measured | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 7.6 | Only Sonar Pro measured |
| Neither model has a result on the other 1 board here | |||
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| Neither model has a result on 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 57.8% | Only Sonar Pro measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 6.6% | Only Sonar Pro measured |
| LMArena Text: hard prompts | 1278 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: expert | 1257 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: hard prompts in English | 1290 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: diagrams | 1119 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: homework | 1158 | Not measured | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| LMArena Text: math | 1261 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: mathematical work | 1271 | Not measured | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 75.5% | Only Sonar Pro measured |
| LMArena Text: science | 1265 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: medicine and healthcare | 1267 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: legal and government | 1271 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: business and finance | 1257 | Not measured | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 12 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index25 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | Leader |
|---|---|---|---|
| LMArena Text | 1277 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: instruction following | 1263 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: creative writing | 1252 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision | 1136 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: English | 1295 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: non-English | 1255 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: Chinese | 1253 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: German | 1266 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: Japanese | 1208 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: Korean | 1207 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: French | 1273 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: Spanish | 1284 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: Russian | 1263 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: Polish | 1242 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: multi-turn | 1270 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: longer queries | 1299 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: writing and language | 1268 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Text: entertainment and media | 1250 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: English | 1157 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: Chinese | 1155 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: reading text | 1132 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: humor | 1142 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: captioning | 1153 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: recognizing things | 1155 | Not measured | Only Mistral Small 3.1 24B measured |
| LMArena Vision: creative writing | 1123 | Not measured | Only Mistral Small 3.1 24B measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mistral Small 3.1 24B | Sonar Pro | 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 3.1 24B costs less
Repository review
50K input + 3K output tokens
Mistral Small 3.1 24B costs less
Agent loop
200K input + 10K output tokens
Mistral Small 3.1 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 Small 3.1 24B | Perplexity Sonar Pro |
|---|---|---|
| Maker | Mistral AI | Perplexity |
| Weights | Open weights | No public weights listed |
| Released | March 17, 2025 | March 7, 2025 |
| Context window | 128K | 200K |
| Input $/Mtok | $0.351 | $3.00 |
| Output $/Mtok | $0.555 | $15.00 |
| 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 Mistral Small 3.1 24B better than Sonar Pro for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Mistral Small 3.1 24B has the edge where output tokens cost 27.0x less.
Which is cheaper, Mistral Small 3.1 24B or Sonar Pro?
Mistral Small 3.1 24B costs $0.351 per million input tokens and $0.555 per million output tokens; Sonar Pro costs $3.00 and $15.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Mistral Small 3.1 24B or Sonar Pro?
Sonar Pro, with 200K tokens against 128K.
How many benchmarks is the Mistral Small 3.1 24B vs Sonar Pro comparison based on?
0 benchmarks have a result for both models as of October 21, 2026. Mistral Small 3.1 24B's coding index rests on 0 independent benchmarks and Sonar Pro's on 0. Where only one model has a result, the page says so instead of naming a winner.