Kimi K2 Thinking vs MiniMax M2.1
Kimi K2 Thinking leads MiniMax M2.1 on the Artificial Analysis Intelligence Index, 22.0 to 20.9, and MiniMax M2.1 costs 2.1x less per output token ($1.20 vs $2.50 per million). Updated October 22, 2026; 25 benchmarks have a result for both.
Kimi K2 Thinking or MiniMax M2.1: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Kimi K2 Thinking for a larger context window (262K against 205K tokens) and work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.
- Shared results
- 25
- Kimi K2 Thinking only
- 5
- MiniMax M2.1 only
- 9
- Like-for-like categories
- 8 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 Thinking
Kimi K2 Thinking leads, 22.0 against 20.9.
Same board, both measured
Reasoning
GPQA Diamond
No call
Tied at 78.5%.
Same board, both measured
Math
AIME
Kimi K2 Thinking
Kimi K2 Thinking leads, 85.4% against 77.9%.
Same board, both measured
Knowledge
MMLU Pro
MiniMax M2.1
MiniMax M2.1 leads, 87.0% against 81.1%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M2.1
MiniMax M2.1 leads, 1201 against 1113.
Same board, both measured
Long documents
Listed context window
Kimi K2 Thinking
Kimi K2 Thinking takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.1
Kimi K2 Thinking $0.0019, MiniMax M2.1 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiniMax M2.1
Kimi K2 Thinking $0.61, MiniMax M2.1 $0.59.
Published attempt cost and pass rate
At a glance
- Coding index
- Kimi K2 Thinking not benchmarked, MiniMax M2.1 not benchmarked.
- Widest category
- Web design, 11.0 points apart on average over 1 shared benchmark.
- Widest single gap
- LiveCodeBench (Vals AI): Kimi K2 Thinking 63.1% against MiniMax M2.1 81.8%, 18.6 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 Thinking $2.50 against MiniMax M2.1 $1.20 per million output tokens, 2.1x apart.
- Context window
- Kimi K2 Thinking takes 262K tokens, MiniMax M2.1 205K.
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 Thinking | Bars | MiniMax M2.1 | Ties |
|---|---|---|---|---|
| Coding | 2 | 4 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | 1 tie | |
| Math | 4 | 0 | ||
| Knowledge | 5 | 2 | ||
| Web design | 0 | 1 | ||
| General | 1 | 1 | ||
| All shared boards | 16 | 8 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index24
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| SWE-bench Verified | 63.4% | Not measured | Only Kimi K2 Thinking measured |
| LiveCodeBench (Vals AI) | 63.1% | 81.8% | MiniMax M2.1 |
| SWE-bench Verified (Vals AI) | 60.2% | 74.8% | MiniMax M2.1 |
| LiveCodeBench (Artificial Analysis run) | 85.3% | 81.0% | Kimi K2 Thinking |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | 28.8% | Kimi K2 Thinking |
| Terminal-Bench | 35.7% | 36.6% | MiniMax M2.1 |
| WeirdML | 42.8% | Not measured | Only Kimi K2 Thinking measured |
| ALE-Bench | 597.5 | 623.8 | MiniMax M2.1 |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.0 | 20.9 | Kimi K2 Thinking |
| Epoch Capabilities Index | 145.8 | Not measured | Only Kimi K2 Thinking measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 93.0% | 85.4% | Kimi K2 Thinking |
| METR time horizons | 59.2% | Not measured | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | 78.5% | Tie |
| GPQA Diamond (Artificial Analysis run) | 83.8% | 83.0% | Kimi K2 Thinking |
| Humanity's Last Exam (Artificial Analysis run) | 23.8% | 23.2% | Kimi K2 Thinking |
| Neither model has a result on the other 19 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| AIME | 85.4% | 77.9% | Kimi K2 Thinking |
| MATH 500 (Vals AI) | Not measured | 89.0% | Only MiniMax M2.1 measured |
| MGSM (Vals AI) | 90.2% | 87.8% | Kimi K2 Thinking |
| AA Math Index | 94.7 | 82.7 | Kimi K2 Thinking |
| AIME 2025 (Artificial Analysis run) | 94.7% | 82.7% | Kimi K2 Thinking |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| MMLU Pro | 81.1% | 87.0% | MiniMax M2.1 |
| LegalBench (Vals AI) | 80.2% | 75.5% | Kimi K2 Thinking |
| CaseLaw (Vals AI) | 65.7% | 55.8% | Kimi K2 Thinking |
| CorpFin (Vals AI) | 60.6% | 58.9% | Kimi K2 Thinking |
| TaxEval (Vals AI) | 71.7% | 66.3% | Kimi K2 Thinking |
| MedQA (Vals AI) | 92.6% | 91.2% | Kimi K2 Thinking |
| MedCode (Vals AI) | Not measured | 34.1% | Only MiniMax M2.1 measured |
| MMLU Pro (Artificial Analysis run) | 84.8% | 87.5% | MiniMax M2.1 |
| Neither model has a result on the other 10 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1113 | 1201 | MiniMax M2.1 |
| Design Arena: UI components | Not measured | 1220 | Only MiniMax M2.1 measured |
| Design Arena: game dev | Not measured | 1134 | Only MiniMax M2.1 measured |
| Design Arena: data viz | Not measured | 1206 | Only MiniMax M2.1 measured |
| Design Arena: 3D | Not measured | 1164 | Only MiniMax M2.1 measured |
| Design Arena: all code categories | Not measured | 1190 | Only MiniMax M2.1 measured |
| Design Arena: SVG | Not measured | 1131 | Only MiniMax M2.1 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 80.8% | Only MiniMax M2.1 measured |
| IFBench | 68.1% | 69.9% | MiniMax M2.1 |
| Long context reasoning (AA-LCR) | 72.0% | 67.7% | Kimi K2 Thinking |
| CL-bench | 17.6% | Not measured | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 Thinking | MiniMax M2.1 | 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
MiniMax M2.1 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.1 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.1 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 Thinking | MiniMax M2.1 |
|---|---|---|
| Maker | Moonshot AI | MiniMax |
| Weights | Open weights | Open weights |
| Released | November 6, 2025 | December 23, 2025 |
| Context window | 262K | 205K |
| Input $/Mtok | $0.60 | $0.30 |
| Output $/Mtok | $2.50 | $1.20 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.61 | $0.59 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2 Thinking better than MiniMax M2.1 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Kimi K2 Thinking for a larger context window (262K against 205K tokens) and work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.
Which is cheaper, Kimi K2 Thinking or MiniMax M2.1?
Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens; MiniMax M2.1 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Kimi K2 Thinking costs $0.61 and MiniMax M2.1 $0.59.
Which has the bigger context window, Kimi K2 Thinking or MiniMax M2.1?
Kimi K2 Thinking, with 262K tokens against 205K.
How many benchmarks is the Kimi K2 Thinking vs MiniMax M2.1 comparison based on?
25 benchmarks have a result for both models as of October 22, 2026. Kimi K2 Thinking's coding index rests on 1 independent benchmark and MiniMax M2.1's on 1. Where only one model has a result, the page says so instead of naming a winner.