Model Comparison

Kimi K2.5 vs Qwen3.5-397B-A17B

Kimi K2.5 shows notably better performance in the majority of benchmarks. Kimi K2.5 is 1.3x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

14 benchmarks

Kimi K2.5 outperforms in 10 benchmarks (AA-LCR, BrowseComp, HMMT 2025, Humanity's Last Exam, IMO-AnswerBench, LiveCodeBench v6, Seal-0, SWE-bench Multilingual, SWE-Bench Verified, WideSearch), while Qwen3.5-397B-A17B is better at 4 benchmarks (GPQA, LongBench v2, MMLU-Pro, Terminal-Bench 2.0).

Kimi K2.5 shows notably better performance in the majority of benchmarks.

Tue Apr 07 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Kimi K2.5 costs less

For input processing, Kimi K2.5 ($0.60/1M tokens) costs the same as Qwen3.5-397B-A17B ($0.60/1M tokens).

For output processing, Kimi K2.5 ($2.50/1M tokens) is 1.4x cheaper than Qwen3.5-397B-A17B ($3.60/1M tokens).

In conclusion, Qwen3.5-397B-A17B is more expensive than Kimi K2.5.*

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

Lowest available price from all providers
Tue Apr 07 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$2.50
Best providerFireworks
Alibaba Cloud / Qwen Team
Qwen3.5-397B-A17B
Input tokens$0.60
Output tokens$3.60
Best providerNovita
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

603.0B diff

Kimi K2.5 has 603.0B more parameters than Qwen3.5-397B-A17B, making it 151.9% larger.

Moonshot AI
Kimi K2.5
1000.0Bparameters
Alibaba Cloud / Qwen Team
Qwen3.5-397B-A17B
397.0Bparameters
1000.0B
Kimi K2.5
397.0B
Qwen3.5-397B-A17B

Context Window

Maximum input and output token capacity

Qwen3.5-397B-A17B accepts 262,144 input tokens compared to Kimi K2.5's 262,100 tokens. Kimi K2.5 can generate longer responses up to 262,100 tokens, while Qwen3.5-397B-A17B is limited to 64,000 tokens.

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
Alibaba Cloud / Qwen Team
Qwen3.5-397B-A17B
Input262,144 tokens
Output64,000 tokens
Tue Apr 07 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Kimi K2.5 and Qwen3.5-397B-A17B support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Kimi K2.5

Text
Images
Audio
Video

Qwen3.5-397B-A17B

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while Qwen3.5-397B-A17B uses Apache 2.0.

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

Kimi K2.5

MIT

Open weights

Qwen3.5-397B-A17B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while Qwen3.5-397B-A17B was released on 2026-02-16.

Qwen3.5-397B-A17B is 1 month newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

2 months ago

Qwen3.5-397B-A17B

Feb 16, 2026

1 months ago

2w newer

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 K2.5 is available from Fireworks. Qwen3.5-397B-A17B is available from Novita.

Kimi K2.5

fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M

Qwen3.5-397B-A17B

novita logo
Novita
Input Price:Input: $0.60/1MOutput Price:Output: $3.60/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Moonshot AI
Less expensive output tokens
Higher AA-LCR score (70.0% vs 68.7%)
Higher BrowseComp score (74.9% vs 69.0%)
Higher HMMT 2025 score (95.4% vs 94.8%)
Higher Humanity's Last Exam score (50.2% vs 28.7%)
Higher IMO-AnswerBench score (81.8% vs 80.9%)
Higher LiveCodeBench v6 score (85.0% vs 83.6%)
Higher Seal-0 score (57.4% vs 46.9%)
Higher SWE-bench Multilingual score (73.0% vs 69.3%)
Higher SWE-Bench Verified score (76.8% vs 76.4%)
Higher WideSearch score (79.0% vs 74.0%)
Alibaba Cloud / Qwen Team

Qwen3.5-397B-A17B

View details

Alibaba Cloud / Qwen Team

Larger context window (262,144 tokens)
Higher GPQA score (88.4% vs 87.6%)
Higher LongBench v2 score (63.2% vs 61.0%)
Higher MMLU-Pro score (87.8% vs 87.1%)
Higher Terminal-Bench 2.0 score (52.5% vs 50.8%)

Detailed Comparison

AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
Alibaba Cloud / Qwen Team
Qwen3.5-397B-A17B

FAQ

Common questions about Kimi K2.5 vs Qwen3.5-397B-A17B

Kimi K2.5 shows notably better performance in the majority of benchmarks. Kimi K2.5 is made by Moonshot AI and Qwen3.5-397B-A17B is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. Qwen3.5-397B-A17B scores MMLU-Redux: 94.9%, HMMT 2025: 94.8%, C-Eval: 93.0%, HMMT25: 92.7%, IFEval: 92.6%.
Both models cost $0.60 per million input tokens.
Kimi K2.5 supports 262K tokens and Qwen3.5-397B-A17B supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (262K vs 262K), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
Kimi K2.5 is developed by Moonshot AI and Qwen3.5-397B-A17B is developed by Alibaba Cloud / Qwen Team.