Ministral 3 3B 2512 vs Reka Flash 3
Reka Flash 3 leads Ministral 3 3B 2512 on the Artificial Analysis Intelligence Index, 6.4 to 4.8, and Ministral 3 3B 2512 costs 2.0x less per output token ($0.10 vs $0.20 per million). Updated October 23, 2026; 1 benchmarks have a result for both.
Ministral 3 3B 2512 or Reka Flash 3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Ministral 3 3B 2512 for output tokens 2.0x cheaper ($0.10 vs $0.20 per million) and a larger context window (131K against 66K tokens).
- Shared results
- 1
- Ministral 3 3B 2512 only
- 6
- Reka Flash 3 only
- 11
- 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
Reka Flash 3
Reka Flash 3 leads, 6.4 against 4.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Ministral 3 3B 2512 has a AA Agentic Index result, 0.8.
Directional only
Web design
Design Arena: websites
No call
Only Ministral 3 3B 2512 has a Design Arena: websites result, 1027.
Directional only
Long documents
Listed context window
Ministral 3 3B 2512
Ministral 3 3B 2512 takes 131K tokens against 66K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Ministral 3 3B 2512
Ministral 3 3B 2512 $0.0001, Reka Flash 3 $0.0002 per turn.
List prices
At a glance
- Coding index
- Ministral 3 3B 2512 not benchmarked, Reka Flash 3 not benchmarked.
- Widest category
- Intelligence, 1.6 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Intelligence Index: Ministral 3 3B 2512 4.8 against Reka Flash 3 6.4, 1.6 points apart on a 0 to 100 scale.
- Output price
- Ministral 3 3B 2512 $0.10 against Reka Flash 3 $0.20 per million output tokens, 2.0x apart.
- Context window
- Ministral 3 3B 2512 takes 131K tokens, Reka Flash 3 66K.
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 3B 2512 | Bars | Reka Flash 3 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index3 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| AA Coding Index | 4.8 | Not measured | Only Ministral 3 3B 2512 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 43.5% | Only Reka Flash 3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 0.0% | Only Reka Flash 3 measured |
| Neither model has a result on the other 40 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 4.8 | 6.4 | Reka Flash 3 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| AA Agentic Index | 0.8 | Not measured | Only Ministral 3 3B 2512 measured |
| τ²-Bench Telecom | Not measured | 0.0% | Only Reka Flash 3 measured |
| BALROG | Not measured | 29.2% | Only Reka Flash 3 measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 52.9% | Only Reka Flash 3 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 4.4% | Only Reka Flash 3 measured |
| Neither model has a result on the other 21 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 33.7 | Only Reka Flash 3 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 33.7% | Only Reka Flash 3 measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 66.9% | Only Reka Flash 3 measured |
| Neither model has a result on the other 19 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1027 | Not measured | Only Ministral 3 3B 2512 measured |
| Design Arena: game dev | 948 | Not measured | Only Ministral 3 3B 2512 measured |
| Design Arena: 3D | 963 | Not measured | Only Ministral 3 3B 2512 measured |
| Design Arena: all code categories | 1009 | Not measured | Only Ministral 3 3B 2512 measured |
| Neither model has a result on the other 5 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 3 | Leader |
|---|---|---|---|
| IFBench | Not measured | 30.4% | Only Reka Flash 3 measured |
| Long context reasoning (AA-LCR) | Not measured | 0.0% | Only Reka Flash 3 measured |
| Neither model has a result on the other 46 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Ministral 3 3B 2512 | Reka Flash 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
Ministral 3 3B 2512 costs less
Repository review
50K input + 3K output tokens
Ministral 3 3B 2512 costs less
Agent loop
200K input + 10K output tokens
Ministral 3 3B 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 3B 2512 | Reka Flash 3 |
|---|---|---|
| Maker | Mistral AI | Reka |
| Weights | Open weights | Open weights |
| Released | December 2, 2025 | March 12, 2025 |
| Context window | 131K | 66K |
| Input $/Mtok | $0.10 | $0.10 |
| Output $/Mtok | $0.10 | $0.20 |
| 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 3B 2512 better than Reka Flash 3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Ministral 3 3B 2512 for output tokens 2.0x cheaper ($0.10 vs $0.20 per million) and a larger context window (131K against 66K tokens).
Which is cheaper, Ministral 3 3B 2512 or Reka Flash 3?
Ministral 3 3B 2512 costs $0.10 per million input tokens and $0.10 per million output tokens; Reka Flash 3 costs $0.10 and $0.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Ministral 3 3B 2512 or Reka Flash 3?
Ministral 3 3B 2512, with 131K tokens against 66K.
How many benchmarks is the Ministral 3 3B 2512 vs Reka Flash 3 comparison based on?
1 benchmarks have a result for both models as of October 23, 2026. Ministral 3 3B 2512's coding index rests on 0 independent benchmarks and Reka Flash 3's on 0. Where only one model has a result, the page says so instead of naming a winner.