Navigate
AI BENCHY
Your ad here

AI BENCHY Compare

ByteDance Seed: Seed-2.0-Lite vs Gemini 3 PRO Preview

Last updated at: 2026-05-01

Metric Seed-2.0-Lite Seed-2.0-Lite medium Release: 2026-02-14 Gemini 3 PRO Preview Gemini 3 PRO Preview medium Release: 2025-11-18
Score 8.6 8.4
Rank #12 #17
Reliability N/A N/A
Consistency 8.8 10.0
Tests Correct
Attempt pass rate 83.3% 77.8%
Flaky tests 3 0
Total Runs 54 54
Cost per result 0.926 1.406
Total Cost $0.121 $0.197
Input Price $0.250 / 1M $0.000 / 1M
Output Price $2.000 / 1M $0.000 / 1M
Output Tokens 3,257 1,508
Reasoning Tokens 52,042 10,084
Response Time (avg) 30.37s 9.06s
Response Time (max) 168.71s 26.24s
Response Time (total) 546.72s 90.58s

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 8.3 10.0 75.0% 0 17.99s 996 7,142
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 14.99s 149 1,485
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 10.0 10.0 100.0% 0 74.49s 436 7,319
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 10.0 10.0 100.0% 0 37.67s 506 4,299
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 10.37s 351 952
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 10.0 10.0 100.0% 0 9.07s 246 1,742
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 10.84s 279 3,156
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 5.9 7.2 55.6% 1 88.74s 15 23,897
Gemini 3 PRO Preview 5.3 10.0 33.3% 0 7.01s 15 1,195
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 6.7 3.6 66.7% 1 18.25s 304 1,620
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 9.34s 78 374
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 10.0 10.0 100.0% 0 7.26s 71 1,480
Gemini 3 PRO Preview 9.8 10.0 100.0% 0 3.26s 69 754
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 9.0 7.9 88.9% 1 11.03s 461 3,532
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 3.91s 243 1,197
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Seed-2.0-Lite 10.0 10.0 100.0% 0 12.38s 222 1,011
Gemini 3 PRO Preview 10.0 10.0 100.0% 0 11.96s 324 971

Quick Compare

Switch Comparison Pair