Kimi K2 0905 vs Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct costs 2.5x less per output token than Kimi K2 0905 ($1.00 vs $2.50 per million). Updated October 22, 2026; 1 benchmarks have a result for both.
Kimi K2 0905 or Qwen2.5 VL 72B Instruct: 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 128K tokens).
- Shared results
- 1
- Kimi K2 0905 only
- 16
- Qwen2.5 VL 72B Instruct only
- 5
- 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
No call
Only Kimi K2 0905 has a AA Intelligence Index result, 15.3.
Directional only
Web design
Design Arena: websites
No call
Only Kimi K2 0905 has a Design Arena: websites result, 1088.
Directional only
Long documents
Listed context window
Kimi K2 0905
Kimi K2 0905 takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 VL 72B Instruct
Kimi K2 0905 $0.0019, Qwen2.5 VL 72B Instruct $0.0013 per turn.
List prices
At a glance
- Coding index
- Kimi K2 0905 not benchmarked, Qwen2.5 VL 72B Instruct not benchmarked.
- Widest category
- Reasoning, 16.2 points apart on average over 1 shared benchmark.
- Widest single gap
- Kagi LLM Benchmark: Kimi K2 0905 52.2% against Qwen2.5 VL 72B Instruct 36.0%, 16.2 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 0905 $2.50 against Qwen2.5 VL 72B Instruct $1.00 per million output tokens, 2.5x apart.
- Context window
- Kimi K2 0905 takes 262K tokens, Qwen2.5 VL 72B Instruct 128K.
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 | Qwen2.5 VL 72B Instruct | Ties |
|---|---|---|---|---|
| Reasoning | 1 | 0 | ||
| All shared boards | 1 | 0 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index4 boards, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| 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 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 15.3 | Not measured | Only Kimi K2 0905 measured |
| 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 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 73.4% | Not measured | Only Kimi K2 0905 measured |
| OSWorld | Not measured | 5.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | 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% | 36.0% | Kimi K2 0905 |
| Neither model has a result on the other 19 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | 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 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 81.9% | Not measured | Only Kimi K2 0905 measured |
| GeoBench | Not measured | 62.0% | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 16 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1088 | Not measured | Only Kimi K2 0905 measured |
| Design Arena: all code categories | 1098 | Not measured | Only Kimi K2 0905 measured |
| Neither model has a result on the other 7 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | 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 |
| LMArena Vision | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: English | Not measured | 1115 | Only Qwen2.5 VL 72B Instruct measured |
| LMArena Vision: Chinese | Not measured | 1107 | Only Qwen2.5 VL 72B Instruct measured |
| Neither model has a result on the other 40 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 0905 | Qwen2.5 VL 72B Instruct | 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
Qwen2.5 VL 72B Instruct costs less
Repository review
50K input + 3K output tokens
Kimi K2 0905 costs less
Agent loop
200K input + 10K output tokens
Kimi K2 0905 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 | Qwen2.5 VL 72B Instruct |
|---|---|---|
| Maker | Moonshot AI | Qwen |
| Weights | Open weights | Open weights |
| Released | September 4, 2025 | February 1, 2025 |
| Context window | 262K | 128K |
| Input $/Mtok | $0.60 | $0.80 |
| Output $/Mtok | $2.50 | $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 Kimi K2 0905 better than Qwen2.5 VL 72B Instruct 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 128K tokens).
Which is cheaper, Kimi K2 0905 or Qwen2.5 VL 72B Instruct?
Kimi K2 0905 costs $0.60 per million input tokens and $2.50 per million output tokens; Qwen2.5 VL 72B Instruct costs $0.80 and $1.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Kimi K2 0905 or Qwen2.5 VL 72B Instruct?
Kimi K2 0905, with 262K tokens against 128K.
How many benchmarks is the Kimi K2 0905 vs Qwen2.5 VL 72B Instruct comparison based on?
1 benchmarks have a result for both models as of October 22, 2026. Kimi K2 0905's coding index rests on 0 independent benchmarks and Qwen2.5 VL 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.