Kimi K2 0711 vs Kimi K2 0905
Kimi K2 0905 leads Kimi K2 0711 on the Artificial Analysis Intelligence Index, 15.3 to 12.7, at about the same output price ($2.50 vs $2.30 per million). Updated October 21, 2026; 16 benchmarks have a result for both.
Kimi K2 0711 or Kimi K2 0905: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Kimi K2 0711 for output tokens 1.1x cheaper ($2.30 vs $2.50 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 16
- Kimi K2 0711 only
- 21
- Kimi K2 0905 only
- 1
- 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 0905
Kimi K2 0905 leads, 15.3 against 12.7.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Kimi K2 0711 has a GPQA Diamond result, 71.5%.
Directional only
Math
AIME
No call
Only Kimi K2 0711 has a AIME result, 62.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Kimi K2 0711 has a MMLU Pro result, 79.4%.
Directional only
Web design
Design Arena: websites
Kimi K2 0905
Kimi K2 0905 leads, 1089 against 1050.
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
Kimi K2 0711
Kimi K2 0711 $0.0017, Kimi K2 0905 $0.0019 per turn.
List prices
At a glance
- Coding index
- Kimi K2 0711 not benchmarked, Kimi K2 0905 not benchmarked.
- Widest category
- Agentic work, 12.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Kimi K2 0711 61.1% against Kimi K2 0905 73.4%, 12.3 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 0711 $2.30 against Kimi K2 0905 $2.50 per million output tokens, 1.1x apart.
- Context window
- Kimi K2 0711 takes 131K tokens, Kimi K2 0905 262K.
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 0711 | Bars | Kimi K2 0905 | Ties |
|---|---|---|---|---|
| Coding | 1 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 2 | 1 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 0 | ||
| Web design | 0 | 2 | ||
| General | 0 | 2 | 1 tie | |
| All shared boards | 4 | 11 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index12
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| Aider polyglot | 59.1% | Not measured | Only Kimi K2 0711 measured |
| SWE-bench Verified | 71.2% | Not measured | Only Kimi K2 0711 measured |
| LiveCodeBench (Vals AI) | 70.5% | Not measured | Only Kimi K2 0711 measured |
| LiveCodeBench (Artificial Analysis run) | 55.6% | 61.0% | Kimi K2 0905 |
| Terminal-Bench Hard (Artificial Analysis run) | 15.9% | 23.5% | Kimi K2 0905 |
| Terminal-Bench | 27.8% | Not measured | Only Kimi K2 0711 measured |
| GSO-Bench | 4.9% | Not measured | Only Kimi K2 0711 measured |
| WeirdML | 39.4% | 36.7% | Kimi K2 0711 |
| ALE-Bench | Not measured | 267.1 | Only Kimi K2 0905 measured |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 15.3 | Kimi K2 0905 |
| Epoch Capabilities Index | 140.0 | Not measured | Only Kimi K2 0711 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 61.1% | 73.4% | Kimi K2 0905 |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| GPQA Diamond | 71.5% | Not measured | Only Kimi K2 0711 measured |
| GPQA Diamond (Artificial Analysis run) | 76.6% | 76.7% | Kimi K2 0905 |
| Humanity's Last Exam (Artificial Analysis run) | 7.4% | 6.4% | Kimi K2 0711 |
| SimpleBench | 26.3% | Not measured | Only Kimi K2 0711 measured |
| Kagi LLM Benchmark | 64.4% | 52.2% | Kimi K2 0711 |
| Neither model has a result on the other 17 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| AIME | 62.7% | Not measured | Only Kimi K2 0711 measured |
| MATH 500 (Vals AI) | 94.2% | Not measured | Only Kimi K2 0711 measured |
| MGSM (Vals AI) | 91.0% | Not measured | Only Kimi K2 0711 measured |
| AA Math Index | 57.0 | 57.3 | Kimi K2 0905 |
| AIME 2025 (Artificial Analysis run) | 57.0% | 57.3% | Kimi K2 0905 |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| MMLU Pro | 79.4% | Not measured | Only Kimi K2 0711 measured |
| LegalBench (Vals AI) | 81.5% | Not measured | Only Kimi K2 0711 measured |
| CorpFin (Vals AI) | 50.4% | Not measured | Only Kimi K2 0711 measured |
| TaxEval (Vals AI) | 70.2% | Not measured | Only Kimi K2 0711 measured |
| MedQA (Vals AI) | 84.0% | Not measured | Only Kimi K2 0711 measured |
| MMLU Pro (Artificial Analysis run) | 82.4% | 81.9% | Kimi K2 0711 |
| Neither model has a result on the other 12 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| Design Arena: websites | 1050 | 1089 | Kimi K2 0905 |
| Design Arena: UI components | 1030 | Not measured | Only Kimi K2 0711 measured |
| Design Arena: game dev | 974 | Not measured | Only Kimi K2 0711 measured |
| Design Arena: data viz | 1018 | Not measured | Only Kimi K2 0711 measured |
| Design Arena: all code categories | 1033 | 1098 | Kimi K2 0905 |
| Neither model has a result on the other 4 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | Leader |
|---|---|---|---|
| IFBench | 41.5% | 41.7% | Kimi K2 0905 |
| Long context reasoning (AA-LCR) | 53.0% | 53.0% | Tie |
| Fiction.LiveBench | 61.1% | 66.7% | Kimi K2 0905 |
| Creative writing (Lech Mazur) | 85.6% | Not measured | Only Kimi K2 0711 measured |
| CL-bench | 11.9% | Not measured | Only Kimi K2 0711 measured |
| Neither model has a result on the other 41 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 0711 | Kimi K2 0905 | 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
Kimi K2 0711 costs less
Repository review
50K input + 3K output tokens
Kimi K2 0711 costs less
Agent loop
200K input + 10K output tokens
Kimi K2 0711 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 0711 | MoonshotAI Kimi K2 0905 |
|---|---|---|
| Maker | Moonshot AI | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | July 11, 2025 | September 4, 2025 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.57 | $0.60 |
| Output $/Mtok | $2.30 | $2.50 |
| 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 0711 better than Kimi K2 0905 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Kimi K2 0711 for output tokens 1.1x cheaper ($2.30 vs $2.50 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, Kimi K2 0711 or Kimi K2 0905?
Kimi K2 0711 costs $0.57 per million input tokens and $2.30 per million output tokens; Kimi K2 0905 costs $0.60 and $2.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Kimi K2 0711 or Kimi K2 0905?
Kimi K2 0905, with 262K tokens against 131K.
How many benchmarks is the Kimi K2 0711 vs Kimi K2 0905 comparison based on?
16 benchmarks have a result for both models as of October 21, 2026. Kimi K2 0711's coding index rests on 0 independent benchmarks and Kimi K2 0905's on 0. Where only one model has a result, the page says so instead of naming a winner.