AI BENCHY
Advertise here
#66

Seed-2.0-Code

Bytedance Seed Release: 2026-08-12 Tested on: 2026-08-12 22:39 bytedance-seed/seed-2.0-code::low
~200B total (~20B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

Seed-2.0-Code scores 7.7 on AI BENCHY and ranks #66. It has 5.7 reliability, a 80.3% pass rate, $0.681 total cost, and 65.89s average response time.

What makes Seed-2.0-Code unique: It stands out most in Data parsing and extraction, where it ranks #1, while Instructions following is its weakest area at #13.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~200B total (~20B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. ByteDance documents the API-only Code model, but does not disclose its architecture or parameter counts; estimate follows the Seed2 production tier.

Parameter source Availability source

Score

7.7

Consistency

7.5

Reliability

5.7

Total Cost (Current Price)

$0.681

Total Output Tokens

212,558

Total Input Tokens

85,648

Input Price

$0.500 / 1M

Output Price

$3.000 / 1M

Tests Correct

Wrong Tests: 9

Attempt pass rate: 80.3%

Flaky tests

7

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

65.89s

Response Time (max): 485.92s

Response Time (total): 1449.53s

Wrong answer: 6 API error: 2 Did not follow instructions: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#66 Seed-2.0-Code

low
Provider returned error
Cost
$0.000
Time
0.3s
Tokens
0 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-12 23:12 $0.500 / 1M $3.000 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Seed-2.0-CodelowvsClaude Opus 4.8lowSeed-2.0-CodelowvsGLM 5mediumSeed-2.0-CodelowvsQwen3.7 FlashhighSeed-2.0-CodelowvsClaude Opus 4.6mediumSeed-2.0-CodelowvsClaude Sonnet 4.6mediumSeed-2.0-CodelowvsGPT-5.6 LunahighSeed-2.0-CodelowvsGPT-5.6 TerramediumSeed-2.0-CodelowvsSolar Pro 4xhighSeed-2.0-CodelowvsGLM 5.2mediumSeed-2.0-CodelowvsDeepSeek V4 Flashhigh

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 7.0 5.0
Combined 7.3 5.8
Data parsing and extraction 10.0 10.0
Domain specific 4.1 4.4
General Intelligence 6.5 3.4
Instructions following 9.8 10.0
Puzzle Solving 9.9 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models