The AI arena is free today

Open Superagent

Kimi K2-Thinking-0905 vs Qwen2.5 72B Instruct

Kimi K2-Thinking-0905 leads the LLM Stats Score 36.0 to 12.1. Qwen2.5 72B Instruct is 2.4x cheaper per token.

Moonshot AI · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Kimi K2-Thinking-0905 leads the overall LLM Stats Score 36.0 to 12.1, ranking #81 overall.

In the 3 individual benchmarks reported for both models, Kimi K2-Thinking-0905 wins 3; this is a narrower head-to-head signal than the composite indexes.

On price, Qwen2.5 72B Instruct is roughly 2.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Kimi K2-Thinking-0905 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Kimi K2-Thinking-0905

  • overall performance matters — it scores 36.0 and ranks #81 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 3 of 3 exact shared results
  • you process long inputs — it offers a 262,144 token context window
  • you want the most recent training data — it shipped Sep 2025

Choose Qwen2.5 72B Instruct

  • cost matters — it's about 2.4x cheaper per token

At a glance

The differences that matter most.

Core performance indexes
36.0
#81
12.1
#253
36.2
#74
12.2
#245
21.0
#91
9.2
#176
Cost, coverage & limits
Benchmark wins
3 of 3
0 of 3
Input price
$0.47 / M
$0.35 / M
Output price
$2.00 / M
$0.40 / M
Context window
262,144
131,072

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Kimi K2-Thinking-0905
Qwen2.5 72B Instruct
38.0#27
17.8#191
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

21 reported for Kimi K2-Thinking-0905 · 14 for Qwen2.5 72B Instruct

3 shared

Kimi K2-Thinking-0905 outperforms in 3 benchmarks (GPQA, MMLU-Pro, MMLU-Redux), while Qwen2.5 72B Instruct is better at 0 benchmarks.

Kimi K2-Thinking-0905 significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Qwen2.5 72B Instruct costs less

For input processing, Kimi K2-Thinking-0905 ($0.47/1M tokens) is 1.3x more expensive than Qwen2.5 72B Instruct ($0.35/1M tokens).

For output processing, Kimi K2-Thinking-0905 ($2.00/1M tokens) is 5.0x more expensive than Qwen2.5 72B Instruct ($0.40/1M tokens).

In conclusion, Kimi K2-Thinking-0905 is more expensive than Qwen2.5 72B Instruct.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
Moonshot AI
Kimi K2-Thinking-0905
Input tokens$0.47
Output tokens$2.00
Best providerDeepinfra
Alibaba Cloud / Qwen Team
Qwen2.5 72B Instruct
Input tokens$0.35
Output tokens$0.40
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

927.3B diff

Kimi K2-Thinking-0905 has 927.3B more parameters than Qwen2.5 72B Instruct, making it 1275.5% larger.

Moonshot AI
Kimi K2-Thinking-0905
1.0Tparameters
Alibaba Cloud / Qwen Team
Qwen2.5 72B Instruct
72.7Bparameters
1000.0B
Kimi K2-Thinking-0905
72.7B
Qwen2.5 72B Instruct

Context Window

Maximum input and output token capacity

Kimi K2-Thinking-0905 accepts 262,144 input tokens compared to Qwen2.5 72B Instruct's 131,072 tokens. Kimi K2-Thinking-0905 can generate longer responses up to 262,144 tokens, while Qwen2.5 72B Instruct is limited to 8,192 tokens.

Moonshot AI
Kimi K2-Thinking-0905
Input262,144 tokens
Output262,144 tokens
Alibaba Cloud / Qwen Team
Qwen2.5 72B Instruct
Input131,072 tokens
Output8,192 tokens
Sun Sep 20 2026 • llm-stats.com

License

Usage and distribution terms

Kimi K2-Thinking-0905 is licensed under MIT, while Qwen2.5 72B Instruct uses Qwen.

License differences may affect how you can use these models in commercial or open-source projects.

Kimi K2-Thinking-0905

MIT

Open weights

Qwen2.5 72B Instruct

Qwen

Open weights

Release Timeline

When each model was launched

Kimi K2-Thinking-0905 was released on 2025-09-05, while Qwen2.5 72B Instruct was released on 2024-09-19.

Kimi K2-Thinking-0905 is 12 months newer than Qwen2.5 72B Instruct.

Kimi K2-Thinking-0905

Sep 5, 2025

1.0 years ago

11mo newer
Qwen2.5 72B Instruct

Sep 19, 2024

2.0 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Kimi K2-Thinking-0905 is available from DeepInfra, Novita, Fireworks. Qwen2.5 72B Instruct is available from DeepInfra, Hyperbolic, Fireworks, Together.

Kimi K2-Thinking-0905

deepinfra logo
Deepinfra
Input Price:Input: $0.47/1MOutput Price:Output: $2.00/1M
novita logo
Novita
Input Price:Input: $0.48/1MOutput Price:Output: $2.00/1M
fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M

Qwen2.5 72B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.35/1MOutput Price:Output: $0.40/1M
hyperbolic logo
Hyperbolic
Input Price:Input: $0.40/1MOutput Price:Output: $0.40/1M
fireworks logo
Fireworks
Input Price:Input: $0.89/1MOutput Price:Output: $0.89/1M
together logo
Together
Input Price:Input: $1.20/1MOutput Price:Output: $1.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Kimi K2-Thinking-0905 and Qwen2.5 72B Instruct side-by-side, then vote on the output you prefer.

Kimi K2-Thinking-0905
✓ Preferred
Qwen2.5 72B Instruct
Open in Playground

FAQ

Common questions about Kimi K2-Thinking-0905 vs Qwen2.5 72B Instruct.

Which is better, Kimi K2-Thinking-0905 or Qwen2.5 72B Instruct?

Kimi K2-Thinking-0905 leads the LLM Stats Score 36.0 to 12.1. Kimi K2-Thinking-0905 is made by Moonshot AI and Qwen2.5 72B Instruct is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Kimi K2-Thinking-0905 compare to Qwen2.5 72B Instruct in benchmarks?

Kimi K2-Thinking-0905 scores AIME 2025: 100.0%, HMMT 2025: 97.5%, MMLU-Redux: 94.4%, FRAMES: 87.0%, MMLU-Pro: 84.6%. Qwen2.5 72B Instruct scores GSM8k: 95.8%, MT-Bench: 93.5%, MBPP: 88.2%, MMLU-Redux: 86.8%, HumanEval: 86.6%.

Is Kimi K2-Thinking-0905 cheaper than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is 1.3x cheaper for input tokens. Kimi K2-Thinking-0905 costs $0.47/M input and $2.00/M output via deepinfra. Qwen2.5 72B Instruct costs $0.35/M input and $0.40/M output via deepinfra.

What are the context window sizes for Kimi K2-Thinking-0905 and Qwen2.5 72B Instruct?

Kimi K2-Thinking-0905 supports 262K tokens and Qwen2.5 72B Instruct supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Kimi K2-Thinking-0905 and Qwen2.5 72B Instruct?

Key differences include LLM Stats Score (36.0 vs 12.1), context window (262K vs 131K), input pricing ($0.47 vs $0.35/M), licensing (MIT vs Qwen). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2-Thinking-0905 and Qwen2.5 72B Instruct?

Kimi K2-Thinking-0905 is developed by Moonshot AI and Qwen2.5 72B Instruct is developed by Alibaba Cloud / Qwen Team.