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。

Gemma 4 31B
DeepMind
Each axis is a category average, normalized to a 100-point radar.
Relative edge: none clear / Relative gap: 编程与软件工程 -5.0
Relative edge: 编程与软件工程 +5.0 / Relative gap: none clear
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 · 78.76
Best single
Kimi K2.5 · AIME 2026 92.50
Modality coverage
Gemma 4 31B · 3 modalities
Head to head
5
Benchmarks
1
Wins
4
Losses
-5.72
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.
5 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Gemma 4 31B | Kimi K2.5 |
|---|---|---|
GPQA Diamond 综合评估 | 84.30Thinking Enabled | 87.60Thinking Enabled |
HLE 综合评估 | 26.50Thinking Enabled | Tools | 50.20Thinking Enabled | Tools |
MMLU Pro 综合评估 | 85.20Thinking Enabled | 78.50Thinking Enabled |
LiveCodeBench 编程与软件工程 | 80.00Thinking Enabled | 85.00Thinking Enabled |
AIME 2026 数学推理 | 89.20Thinking Enabled | 92.50Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Gemma 4 31BDeepMind | Kimi K2.5Moonshot AI |
|---|---|---|
Core specsRelease | 2026-04-02 | 2026-01-27 |
Context length | 256K | 256K |
Parameters | 31 | 10000 |
Active parameters | 31 | 320 |
Max output | 32768 | 16384 |
MoE | No | Yes |
Supported modes | No mode data | 常规模式(Non-Thinking Mode)思考模式(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 | / | / |
Video Input/Output | / | Not provided |
ResourcesPaper / report | Gemma 4: Byte for byte, the most capable open models | Kimi K2.5: Visual Agentic Intelligence |
DataLearner blog | Google Gemma 4 正式开源:Apache 2.0 协议、手机端可运行、原生支持多模态和 Agent 工作流 | 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 K2.5
Moonshot AI