Qwen3.6-35B-A3B Benchmark Details

Qwen3.6-35B-A3B currently shows benchmark results led by GPQA (2 / 17, score 86), C-Eval (7 / 48, score 90), MMLU Pro (25 / 134, score 85.20). This page also compares it with 3 competitor models and 1 predecessor or same-series models, including performance and pricing views when available.

Benchmark Results

Qwen3.6-35B-A3B

Benchmark Results

General Knowledge

4 evaluations

Benchmark / mode

Score

Rank/total

C-Eval

Thinking Mode

7 / 48

GPQA

Thinking Mode

2 / 17

MMLU Pro

Thinking Mode

85.20

25 / 134

HLE

Thinking Mode

21.40

137 / 197

Other

1 evaluations

Benchmark / mode

Score

Rank/total

GPQA Diamond

Standard Mode

84.85

103 / 274

Coding and Software Engineer

4 evaluations

Benchmark / mode

Score

Rank/total

LiveCodeBench

Thinking Mode

80.40

31 / 128

SWE-bench Verified

Thinking Mode

73.40

48 / 116

SWE-bench Multilingual

Thinking Mode

67.20

26 / 29

SWE-Bench Pro - Public

Thinking Mode

49.50

49 / 62

AI Agent - Tool Usage

2 evaluations

Benchmark / mode

Score

Rank/total

Terminal Bench 2.0

Thinking Mode

51.50

33 / 48

Tool Decathlon

Thinking Mode

26.90

10 / 10

Text Embedding

2 evaluations

Benchmark / mode

Score

Rank/total

Context Arena

Standard Mode

53.20

84 / 126

Context Arena

Thinking Mode

83.53

27 / 126

Math and Reasoning

2 evaluations

Benchmark / mode

Score

Rank/total

AIME 2026

Thinking Mode

92.70

10 / 21

IMO-AnswerBench

Thinking Mode

78.90

21 / 24

Compare with other models

Competitor Comparison

Benchmark scores for Qwen3.6-35B-A3B compared against top models in its class

Qwen3.6-35B-A3BGemma 4 26B A4B GLM-4.7-Flash Mistral Medium 3.5

Benchmark categories:

The chart shows each model’s highest score per benchmark within the current filter. Out-of-100 benchmarks use raw heights; out-of-range benchmarks are scaled within that benchmark while labels keep the original scores.

7 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.

Benchmark	Qwen3.6-35B-A3BCurrent	Gemma 4 26B A4B	GLM-4.7-Flash	Mistral Medium 3.5
HLE Accuracy 综合评估	21.40Thinking Enabled	17.20Thinking Enabled ｜ Tools	14.40Thinking Enabled	--
MMLU Pro Accuracy 综合评估	85.20Thinking Enabled	82.60Thinking Enabled	--	--
GPQA Diamond Accuracy 科学与综合推理	84.85Standard Mode	82.30Thinking Enabled	75.20Thinking Enabled	--
LiveCodeBench Pass @K 编程与软件工程	80.40Thinking Enabled	77.10Thinking Enabled	--	--
SWE-bench Verified Accuracy 编程与软件工程	73.40Thinking Enabled	--	59.20Thinking Enabled	--
Context Arena Accuracy (8 needles, 4K-128K context) 文本向量检索	83.53Thinking Enabled	--	--	32.05Thinking Level · High
AIME 2026 Accuracy 数学推理	92.70Thinking Enabled	88.30Thinking Enabled	--	--

Standard API Pricing: Qwen3.6-35B-A3B vs. Peer Models

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier. · CNY / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
GLM-4.7-Flash	智谱AI	¥0 / 1M tokens	¥0 / 1M tokens	—

Version History

How each version of the Qwen3.6-35B-A3B series stacks up on benchmark tests

Qwen3.6-35B-A3BQwen3.5-35B-A3B

Benchmark categories:

1 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.

Benchmark	Qwen3.6-35B-A3BCurrent	Qwen3.5-35B-A3B
Context Arena Accuracy (8 needles, 4K-128K context) 文本向量检索	83.53Thinking Enabled	67.48Thinking Enabled

Single-Benchmark Version Trend

Viewing: Context Arena · 文本向量检索

Benchmark

NormalNormal + ToolsThinkingThinking + ToolsDeepDeep + Tools

X-axis shows model and release date, Y-axis shows score; solid lines connect the same mode across versions, while dotted guides align modes within the same generation.

Standard API Pricing Across the Qwen3.6-35B-A3B Series

Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.

Source: DataLearnerAI. Standard text prices shown here use the default supplier.

Comparable standard text pricing is not available for these models.