See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
Kimi K2.5
Moonshot AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 编程与软件工程 +28.2 / Relative gap: none clear
Relative edge: none clear / Relative gap: 编程与软件工程 -28.2
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Kimi K2.5 · 65.61
Best single
Kimi K2.5 · AIME2025 96.10
Modality coverage
Kimi K2.5 · 2 modalities
Head to head
9
Benchmarks
8
Wins
1
Losses
+25.61
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
9 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Kimi K2.5 | Kimi K2 |
|---|---|---|
ARC-AGI 综合评估 | 65.30Thinking Enabled | 13.30Standard Mode |
GPQA Diamond 综合评估 | 87.60Thinking Enabled | 75.10Standard Mode |
HLE 综合评估 | 50.20Thinking Enabled ｜ Tools | 4.70Standard Mode |
MMLU Pro 综合评估 | 78.50Thinking Enabled | 81.10Standard Mode |
LiveCodeBench 编程与软件工程 | 85.00Thinking Enabled | 53.70Standard Mode |
SWE-bench Verified 编程与软件工程 | 76.80Thinking Enabled ｜ Tools | 51.80Standard Mode |
AIME2025 数学推理 | 96.10Thinking Enabled | 54.00Standard Mode |
4.20Standard Mode | 0.01Standard Mode | |
Simple Bench 常识推理 | 46.80Thinking Enabled | 26.30Standard Mode |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Kimi K2.5Moonshot AI | Kimi K2Moonshot AI |
|---|---|---|
Core specsRelease | 2026-01-27 | 2025-07-11 |
Context length | 256K | 131K |
Parameters | 10000 | 10000 |
Active parameters | 320 | 320 |
Max output | 16384 | 134144 |
MoE | Yes | Yes |
Supported modes | 常规模式（Non-Thinking Mode）思考模式（Thinking Mode） | 常规模式（Non-Thinking Mode） |
LicenseCode Open Source | Not provided | Not provided |
Weights Open Source | Not provided | Not provided |
Commercial use | 免费商用授权 | 免费商用授权 |
Modality supportText Input/Output | / | / |
Image Input/Output | / | Not provided |
ResourcesPaper / report | Kimi K2.5: Visual Agentic Intelligence | Kimi K2: Open Agentic Intelligence |
DataLearner blog | 重磅！Kimi K2.5发布，依然免费开源！原生多模态MoE架构，全球最大规模参数的开源模型之一，官方评测结果比肩诸多闭源模型！可以驱动100个子Agent执行！ | Kimi开源K2大模型：全球首个开源可商用的1万亿参数规模大模型，MoE架构，评测结果与DeepSeekV3相当，但模型文件有1TB！ |
Kimi K2
Moonshot AI
