Kimi K2-Thinking-0905 vs Qwen3.5-122B-A10B
Kimi K2-Thinking-0905 and Qwen3.5-122B-A10B are closely matched at 35.5 and 34.7 on the LLM Stats Score. Qwen3.5-122B-A10B is 1.0x cheaper per token.
Moonshot AI · Alibaba Cloud / Qwen Team · Updated for 2026
Which is better?
Kimi K2-Thinking-0905 and Qwen3.5-122B-A10B are closely matched on the overall LLM Stats Score at 35.5 and 34.7.
In the 11 individual benchmarks reported for both models, Kimi K2-Thinking-0905 wins 6; this is a narrower head-to-head signal than the composite indexes.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Kimi K2-Thinking-0905
- you value its reported benchmark strengths — it wins 6 of 11 exact shared results
Choose Qwen3.5-122B-A10B
- you want the most recent training data — it shipped Feb 2026
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
21 reported for Kimi K2-Thinking-0905 · 81 for Qwen3.5-122B-A10B
Kimi K2-Thinking-0905 outperforms in 6 benchmarks (HMMT 2025, Humanity's Last Exam, LiveCodeBench v6, MMLU-Redux, OJBench, Seal-0), while Qwen3.5-122B-A10B is better at 5 benchmarks (BrowseComp, BrowseComp-zh, GPQA, MMLU-Pro, SWE-Bench Verified).
Kimi K2-Thinking-0905 has a slight edge in benchmark performance.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Kimi K2-Thinking-0905 ($0.47/1M tokens) is 1.6x more expensive than Qwen3.5-122B-A10B ($0.29/1M tokens).
For output processing, Kimi K2-Thinking-0905 ($2.00/1M tokens) is 1.2x cheaper than Qwen3.5-122B-A10B ($2.40/1M tokens).
In conclusion, Kimi K2-Thinking-0905 is more expensive than Qwen3.5-122B-A10B.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Kimi K2-Thinking-0905 has 878.0B more parameters than Qwen3.5-122B-A10B, making it 719.7% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 262,144 tokens. Both models can generate responses up to 262,144 tokens.
Input capabilities
Documented input modalities across available providers
Qwen3.5-122B-A10B supports multimodal inputs, whereas Kimi K2-Thinking-0905 does not.
Qwen3.5-122B-A10B can handle both text and other forms of data like images, making it suitable for multimodal applications.
Kimi K2-Thinking-0905
Qwen3.5-122B-A10B
License
Usage and distribution terms
Kimi K2-Thinking-0905 is licensed under MIT, while Qwen3.5-122B-A10B uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
MIT
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Kimi K2-Thinking-0905 was released on 2025-09-05, while Qwen3.5-122B-A10B was released on 2026-02-24.
Qwen3.5-122B-A10B is 6 months newer than Kimi K2-Thinking-0905.
Sep 5, 2025
1.1 years ago
Feb 24, 2026
8 months ago
5mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Kimi K2-Thinking-0905 is available from DeepInfra, Novita, Fireworks. Qwen3.5-122B-A10B is available from DeepInfra, Novita.
Kimi K2-Thinking-0905
Qwen3.5-122B-A10B
Outputs Comparison
Judge for yourself.
Run your own prompts against Kimi K2-Thinking-0905 and Qwen3.5-122B-A10B side-by-side, then vote on the output you prefer.
FAQ
Common questions about Kimi K2-Thinking-0905 vs Qwen3.5-122B-A10B.