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
Best overall
Gemma 4 31B · 83.17
Best single
Gemma 4 31B · MMLU Pro 85.20
Modality coverage
Gemma 3 - 27B (IT) · 2 modalities
Head to head
3
Benchmarks
0
Wins
3
Losses
-36.63
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.
3 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Gemma 3 - 27B (IT) | Gemma 4 31B |
|---|---|---|
GPQA Diamond 综合评估 | 42.40Standard Mode | 84.30Thinking Enabled |
MMLU Pro 综合评估 | 67.50Standard Mode | 85.20Thinking Enabled |
LiveCodeBench 编程与软件工程 | 29.70Standard Mode | 80.00Thinking Enabled |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Gemma 3 - 27B (IT)Google Deep Mind | Gemma 4 31BDeepMind |
|---|---|---|
Core specsRelease | 2025-03-12 | 2026-04-02 |
Context length | 128K | 256K |
Parameters | 270 | 307 |
Max output | Not provided | 32768 |
MoE | No | No |
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 | / | / |
ResourcesPaper / report | Gemma 3 Technical Report | Gemma 4 Model Card |
DataLearner blog | Google开源第三代Gemma-3系列模型：支持多模态、最多128K输入，其中Gemma 3-27B在大模型匿名竞技场得分超过了Qwen2.5-Max | 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 |
