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。

Qwen3-8B
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 编程与软件工程 +7.4 / Relative gap: none clear
Relative edge: none clear / Relative gap: 编程与软件工程 -7.4
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
Pangu Embedded · 77.68
Best single
Qwen3-8B · MATH-500 97.40
Modality coverage
Pangu Embedded · 1 modalities
Head to head
5
Benchmarks
4
Wins
1
Losses
+3.06
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 | Pangu Embedded | Qwen3-8B |
|---|---|---|
GPQA 综合评估 | 68.00Standard Mode | 62.00Standard Mode |
MMLU Pro 综合评估 | 79.00Standard Mode | 72.50Standard Mode |
AIME 2024 数学推理 | 81.90Standard Mode | 79.40Standard Mode |
MATH-500 数学推理 | 92.40Standard Mode | 97.40Thinking Enabled |
LiveCodeBench 编程与软件工程 | 67.10Standard Mode | 61.80Standard Mode |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Pangu Embedded华为 | Qwen3-8B阿里巴巴 |
|---|---|---|
Core specsRelease | 2025-06-30 | 2025-04-28 |
Context length | 32K | 128K |
Parameters | 70 | 80 |
Active parameters | 70 | 80 |
Max output | 32768 | 129024 |
MoE | No | No |
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 | / | / |
ResourcesPaper / report | Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition | |
DataLearner blog | https://www.datalearner.com/blog/1051751273565225 | 重磅!阿里开源第三代千问大模型:Qwen3系列,最小仅6亿参数规模,最大2350亿参数规模大模型! |
阿里巴巴