AI BENCHY
Advertise here
#99

Seed-2.0-Lite

Bytedance Seed Release: 2026-02-14 Tested on: 2026-05-22 00:33 bytedance-seed/seed-2.0-lite::none
(medium) (none)

Summary

Seed-2.0-Lite scores 5.9 on AI BENCHY and ranks #99. It has 10.0 reliability, a 50.0% pass rate, $0.018 total cost, and 2.44s average response time.

What makes Seed-2.0-Lite unique: It stands out most in General Intelligence, where it ranks #1, while Anti-AI Tricks is its weakest area at #13.

Score

5.9

Consistency

7.9

Total Output Tokens

3,164

Total Input Tokens

0

Input Price

$0.250 / 1M

Output Price

$2.000 / 1M

Tests Correct

Wrong Tests: 12

Attempt pass rate: 50.0%

Flaky tests

5

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

Response Time (avg)

2.44s

Response Time (max): 6.70s

Response Time (total): 48.71s

Generation showcase

Hamster playing table tennis

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

#99 Seed-2.0-Lite

none
Cost
$0.005
Time
83.8s
Tokens
2,311 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 14:17 New test added 5.8 10.0 $0.019 Compare
2026-05-22 00:33 Suite changed 5.9 10.0 $0.018 Current run
2026-04-11 01:44 First recorded run 6.2 N/A $0.016 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-22 00:33 · Suite changed5.97.910.08/2053,1640$0.0182.44s
2026-04-11 01:44 · First recorded run6.27.7N/A8/1853,1290$0.0162.53s
Difference-0.3+0.200+350+$0.002-90ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

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

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.0 5.9
Coding 6.8 9.9
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.6 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 5.2 4.4
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models