Ministral 3 8B 2512 vs Sonar
Sonar leads Ministral 3 8B 2512 on the Artificial Analysis Intelligence Index, 7.7 to 5.5, and Ministral 3 8B 2512 costs 6.7x less per output token ($0.15 vs $1.00 per million). Updated October 21, 2026; 1 benchmarks have a result for both.
Ministral 3 8B 2512 or Sonar: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Ministral 3 8B 2512 for output tokens 6.7x cheaper ($0.15 vs $1.00 per million) and a larger context window (262K against 127K tokens).
- Shared results
- 1
- Ministral 3 8B 2512 only
- 6
- Sonar only
- 4
- Like-for-like categories
- 1 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
Sonar
Sonar leads, 7.7 against 5.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Ministral 3 8B 2512 has a AA Agentic Index result, 0.6.
Directional only
Web design
Design Arena: websites
No call
Only Ministral 3 8B 2512 has a Design Arena: websites result, 1065.
Directional only
Long documents
Listed context window
Ministral 3 8B 2512
Ministral 3 8B 2512 takes 262K tokens against 127K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Ministral 3 8B 2512
Ministral 3 8B 2512 $0.0002, Sonar $0.0015 per turn.
List prices
At a glance
- Coding index
- Ministral 3 8B 2512 not benchmarked, Sonar not benchmarked.
- Widest category
- Intelligence, 2.2 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Intelligence Index: Ministral 3 8B 2512 5.5 against Sonar 7.7, 2.2 points apart on a 0 to 100 scale.
- Output price
- Ministral 3 8B 2512 $0.15 against Sonar $1.00 per million output tokens, 6.7x apart.
- Context window
- Ministral 3 8B 2512 takes 262K tokens, Sonar 127K.
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 | Ministral 3 8B 2512 | Bars | Sonar | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index2 boards, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| AA Coding Index | 9.7 | Not measured | Only Ministral 3 8B 2512 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 29.5% | Only Sonar measured |
| Neither model has a result on the other 36 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| AA Intelligence Index | 5.5 | 7.7 | Sonar |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| AA Agentic Index | 0.6 | Not measured | Only Ministral 3 8B 2512 measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 47.1% | Only Sonar measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 4.9% | Only Sonar measured |
| Neither model has a result on the other 19 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| Neither model has a result on 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 68.9% | Only Sonar measured |
| Neither model has a result on the other 16 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| Design Arena: websites | 1065 | Not measured | Only Ministral 3 8B 2512 measured |
| Design Arena: game dev | 990 | Not measured | Only Ministral 3 8B 2512 measured |
| Design Arena: 3D | 1032 | Not measured | Only Ministral 3 8B 2512 measured |
| Design Arena: all code categories | 1053 | Not measured | Only Ministral 3 8B 2512 measured |
| Neither model has a result on the other 5 boards here | |||
GeneralNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | Leader |
|---|---|---|---|
| Neither model has a result on 46 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ministral 3 8B 2512 | Sonar | 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
Ministral 3 8B 2512 costs less
Repository review
50K input + 3K output tokens
Ministral 3 8B 2512 costs less
Agent loop
200K input + 10K output tokens
Ministral 3 8B 2512 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 Ministral 3 8B 2512 | Perplexity Sonar |
|---|---|---|
| Maker | Mistral AI | Perplexity |
| Weights | Open weights | No public weights listed |
| Released | December 2, 2025 | January 27, 2025 |
| Context window | 262K | 127K |
| Input $/Mtok | $0.15 | $1.00 |
| Output $/Mtok | $0.15 | $1.00 |
| 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 Ministral 3 8B 2512 better than Sonar for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Ministral 3 8B 2512 for output tokens 6.7x cheaper ($0.15 vs $1.00 per million) and a larger context window (262K against 127K tokens).
Which is cheaper, Ministral 3 8B 2512 or Sonar?
Ministral 3 8B 2512 costs $0.15 per million input tokens and $0.15 per million output tokens; Sonar costs $1.00 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Ministral 3 8B 2512 or Sonar?
Ministral 3 8B 2512, with 262K tokens against 127K.
How many benchmarks is the Ministral 3 8B 2512 vs Sonar comparison based on?
1 benchmarks have a result for both models as of October 21, 2026. Ministral 3 8B 2512's coding index rests on 0 independent benchmarks and Sonar's on 0. Where only one model has a result, the page says so instead of naming a winner.