Kimi K2 0905 vs Ministral 3 3B 2512
Kimi K2 0905 leads Ministral 3 3B 2512 on the Artificial Analysis Intelligence Index, 15.3 to 4.8, and Ministral 3 3B 2512 costs 25.0x less per output token ($0.10 vs $2.50 per million). Updated October 22, 2026; 3 benchmarks have a result for both.
Kimi K2 0905 or Ministral 3 3B 2512: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Kimi K2 0905 for a larger context window (262K against 131K tokens).
- Shared results
- 3
- Kimi K2 0905 only
- 14
- Ministral 3 3B 2512 only
- 4
- Like-for-like categories
- 2 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
Kimi K2 0905
Kimi K2 0905 leads, 15.3 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
Kimi K2 0905
Kimi K2 0905 leads, 1088 against 1027.
Same board, both measured
Long documents
Listed context window
Kimi K2 0905
Kimi K2 0905 takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Ministral 3 3B 2512
Kimi K2 0905 $0.0019, Ministral 3 3B 2512 $0.0001 per turn.
List prices
At a glance
- Coding index
- Kimi K2 0905 not benchmarked, Ministral 3 3B 2512 not benchmarked.
- Widest category
- Intelligence, 10.5 points apart on average over 1 shared benchmark.
- Widest single gap
- Design Arena: all code categories: Kimi K2 0905 1098 against Ministral 3 3B 2512 1009, 11.1 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 0905 $2.50 against Ministral 3 3B 2512 $0.10 per million output tokens, 25.0x apart.
- Context window
- Kimi K2 0905 takes 262K tokens, Ministral 3 3B 2512 131K.
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 | Kimi K2 0905 | Bars | Ministral 3 3B 2512 | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Web design | 2 | 0 | ||
| All shared boards | 3 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index5 boards, none shared
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 4.8 | Only Ministral 3 3B 2512 measured |
| LiveCodeBench (Artificial Analysis run) | 61.0% | Not measured | Only Kimi K2 0905 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 23.5% | Not measured | Only Kimi K2 0905 measured |
| WeirdML | 36.7% | Not measured | Only Kimi K2 0905 measured |
| ALE-Bench | 267.1 | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 38 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| AA Intelligence Index | 15.3 | 4.8 | Kimi K2 0905 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 0.8 | Only Ministral 3 3B 2512 measured |
| τ²-Bench Telecom | 73.4% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 76.7% | Not measured | Only Kimi K2 0905 measured |
| Humanity's Last Exam (Artificial Analysis run) | 6.4% | Not measured | Only Kimi K2 0905 measured |
| Kagi LLM Benchmark | 52.2% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 20 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| AA Math Index | 57.3 | Not measured | Only Kimi K2 0905 measured |
| AIME 2025 (Artificial Analysis run) | 57.3% | Not measured | Only Kimi K2 0905 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 | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 19 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| Design Arena: websites | 1088 | 1027 | Kimi K2 0905 |
| Design Arena: game dev | Not measured | 948 | Only Ministral 3 3B 2512 measured |
| Design Arena: 3D | Not measured | 962 | Only Ministral 3 3B 2512 measured |
| Design Arena: all code categories | 1098 | 1009 | Kimi K2 0905 |
| Neither model has a result on the other 5 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | Leader |
|---|---|---|---|
| IFBench | 41.7% | Not measured | Only Kimi K2 0905 measured |
| Long context reasoning (AA-LCR) | 53.0% | Not measured | Only Kimi K2 0905 measured |
| Fiction.LiveBench | 66.7% | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 45 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 0905 | Ministral 3 3B 2512 | 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 | MoonshotAI Kimi K2 0905 | Mistral Ministral 3 3B 2512 |
|---|---|---|
| Maker | Moonshot AI | Mistral AI |
| Weights | Open weights | Open weights |
| Released | September 4, 2025 | December 2, 2025 |
| Context window | 262K | 131K |
| Input $/Mtok | $0.60 | $0.10 |
| Output $/Mtok | $2.50 | $0.10 |
| 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 Kimi K2 0905 better than Ministral 3 3B 2512 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Kimi K2 0905 for a larger context window (262K against 131K tokens).
Which is cheaper, Kimi K2 0905 or Ministral 3 3B 2512?
Kimi K2 0905 costs $0.60 per million input tokens and $2.50 per million output tokens; Ministral 3 3B 2512 costs $0.10 and $0.10. Cost per solved task is known for neither of them.
Which has the bigger context window, Kimi K2 0905 or Ministral 3 3B 2512?
Kimi K2 0905, with 262K tokens against 131K.
How many benchmarks is the Kimi K2 0905 vs Ministral 3 3B 2512 comparison based on?
3 benchmarks have a result for both models as of October 22, 2026. Kimi K2 0905's coding index rests on 0 independent benchmarks and Ministral 3 3B 2512's on 0. Where only one model has a result, the page says so instead of naming a winner.