Seed2.1 Pro Benchmark Details

Seed2.1 Pro currently shows benchmark results led by SciCode (2 / 15, score 59.80), MMMU-Pro (2 / 8, score 82.70), MathVision (4 / 12, score 94.50). 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

Seed2.1 Pro

Benchmark Results

AI Agent - Tool Usage

1 evaluations

Benchmark / mode

Score

Rank/total

Terminal-Bench 2.1

Thinking ModeTools

36 / 49

Multimodal Understanding

7 evaluations

Benchmark / mode

Score

Rank/total

MathVision

Thinking Mode

92.60

6 / 12

MathVision

Thinking ModeTools

94.50

4 / 12

CharXiv RQ

Thinking Mode

85.40

9 / 19

CharXiv RQ

Thinking ModeTools

86.40

7 / 19

MMMU-Pro

Thinking Mode

81.60

4 / 8

MMMU-Pro

Thinking ModeTools

82.70

2 / 8

BabyVision

Thinking Mode

73.70

4 / 6

Coding and Software Engineer

1 evaluations

Benchmark / mode

Score

Rank/total

SciCode

Thinking Mode

59.80

2 / 15

Compare with other models

Competitor Comparison

Benchmark scores for Seed2.1 Pro compared against top models in its class

Seed2.1 ProQwen3.7 Max GLM-5.2 DeepSeek-V4-Pro

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.

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

Benchmark	Seed2.1 ProCurrent	Qwen3.7 Max	GLM-5.2	DeepSeek-V4-Pro
Terminal-Bench 2.1 Accuracy AI Agent - 工具使用	71.00Thinking Enabled ｜ Tools	--	81.00Thinking Level · High ｜ Tools	87.90Thinking Level · Extra High ｜ Tools
SciCode Score 编程与软件工程	59.80Thinking Enabled	53.50Thinking Level · High	--	--

Standard API Pricing: Seed2.1 Pro 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.

These models use different currencies or billing units, so the page falls back to raw price values instead of a shared bar chart.

Seed2.1 Pro

Supplier: 字节跳动Seed团队

Standard input: ¥6 / 1M tokens

Standard output: ¥30 / 1M tokens

Qwen3.7 Max

Supplier: 阿里巴巴

Standard input: ¥12 / 1M tokens

Standard output: ¥36 / 1M tokens

GLM-5.2

Supplier: 智谱AI

Standard input: $1.4 / 1M tokens

Standard output: $4.4 / 1M tokens

DeepSeek-V4-Pro

Supplier: DeepSeek-AI

Standard input: $0.435 / 1M tokens

Standard output: $0.87 / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
Seed2.1 Pro	字节跳动Seed团队	¥6 / 1M tokens	¥30 / 1M tokens	—
Qwen3.7 Max	阿里巴巴	¥12 / 1M tokens	¥36 / 1M tokens	—
GLM-5.2	智谱AI	$1.4 / 1M tokens	$4.4 / 1M tokens	—
DeepSeek-V4-Pro	DeepSeek-AI	$0.435 / 1M tokens	$0.87 / 1M tokens	—

Version History

How each version of the Seed2.1 Pro series stacks up on benchmark tests

Seed2.1 ProDoubao Seed 2.0 Pro

No benchmark data matches the selected filters.

Standard API Pricing Across the Seed2.1 Pro 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. · CNY / 1M tokens

Model	Supplier	Standard input	Standard output	Base price applies to
Seed2.1 Pro	字节跳动Seed团队	¥6 / 1M tokens	¥30 / 1M tokens	—
Doubao Seed 2.0 Pro	字节跳动Seed团队	¥3.2 / 1M tokens	¥16 / 1M tokens	—