#68 Seed-2.0-Mini
medium- Cost
- $0.002
- Time
- 161.7s
- Tokens
- 4,379 tok
Bytedance Seed
Release: 2026-02-14
Tested on: 2026-05-22 00:44
bytedance-seed/seed-2.0-mini::medium
~50B total (~5B active)MoEClosedEstimated Summary
Seed-2.0-Mini scores 7.1 on AI BENCHY and ranks #68. It has 5.0 reliability, a 60.0% pass rate, $0.044 total cost, and 79.17s average response time.
What makes Seed-2.0-Mini unique: Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- Parameters
- ~50B total (~5B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Seed2 tiers are public, but their parameter counts are not.
7.1
Consistency
9.2
5.0
$0.044
Total Output Tokens
97,852
Total Input Tokens
0
Input Price
$0.100 / 1M
Output Price
$0.400 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 03:01 Re-test | 7.0 | 8.7 | $0.116 | Compare | |
| 2026-07-16 23:23 New test added | 7.0 | 8.5 | $0.101 | Compare | |
| 2026-06-04 14:36 New test added | 6.9 | 6.7 | $0.044 | Compare | |
| 2026-05-22 00:44 Suite changed | 7.1 | 5.0 | $0.044 | Current run | |
| 2026-04-11 01:44 First recorded run | 7.5 | N/A | $0.037 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-22 00:44 · Suite changed | 60/60 attempts | 7.1 | 9.2 | 5.0 | 11/20 | 2 | 97,852 | 0 | $0.044 | 79.17s |
| 2026-08-14 03:01 · Re-test | 66/66 attempts | 7.0 | 8.9 | 8.7 | 11/22 | 3 | 258,322 | 125,704 | $0.116 | 93.10s |
| Difference | — | +0.1 | +0.3 | -3.7 | 0 | -1 | -160470 | -125704 | -$0.073 | -13930ms |
Benchmark coverage differs: 60/60 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
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.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Seed-2.0-MinimediumvsGrok 4.20mediumSeed-2.0-MinimediumvsKimi K2.5mediumSeed-2.0-MinimediumvsMercury 2mediumSeed-2.0-MinimediumvsKAT-Coder-Pro V2.5mediumSeed-2.0-MinimediumvsGPT-5.5noneSeed-2.0-MinimediumvsQwen3.7 FlashmediumSeed-2.0-MinimediumvsGLM 5.1mediumSeed-2.0-MinimediumvsSeed-2.0-CodehighSeed-2.0-MinimediumvsDeepSeek V3.2mediumSeed-2.0-MinimediumvsGemini 3.5 Flashnone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 6.6 | 10.0 | |
| Coding | 6.8 | 9.8 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.0 | 10.0 | |
| General Intelligence | 5.1 | 3.4 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 8.2 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |