The AI arena is free today

Open Superagent

Seed 1.8 vs Seed 2.0 Mini

Seed 1.8 leads the LLM Stats Score 34.2 to 27.9. Seed 2.0 Mini is 3.9x cheaper per token.

ByteDance · ByteDance · Updated for 2026

Which is better?

Seed 1.8 leads the overall LLM Stats Score 34.2 to 27.9, ranking #91 overall.

In the 42 individual benchmarks reported for both models, Seed 1.8 wins 37; this is a narrower head-to-head signal than the composite indexes.

On price, Seed 2.0 Mini is roughly 3.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Seed 1.8

  • overall performance matters — it scores 34.2 and ranks #91 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 37 of 42 exact shared results

Choose Seed 2.0 Mini

  • cost matters — it's about 3.9x cheaper per token

At a glance

The differences that matter most.

Core performance indexes
34.2
#91
27.9
#135
33.5
#93
28.8
#123
19.8
#99
1.5
#229
14.9
#86
1.3
#167
Cost, coverage & limits
Benchmark wins
37 of 42
5 of 42
Input price
$0.25 / M
$0.10 / M
Output price
$2.00 / M
$0.40 / M
Context window
256,000
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

6 shared
Index
Seed 1.8
Seed 2.0 Mini
32.5#57
26.7#100
24.1#51
18.0#79
19.7#32
16.9#43
27.4#38
21.5#63
32.7#13
26.3#48
1 more shared indexes
32.7#13
26.3#38
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

57 reported for Seed 1.8 · 83 for Seed 2.0 Mini

42 shared

Seed 1.8 outperforms in 37 benchmarks (AetherCode, AIME 2025, ARC-AGI, Beyond AIME, BLINK, CharXiv-R, CountBench, DUDE, DynaMath, EMMA, ERQA, LiveCodeBench v6, LiveSports-3K, LongVideoBench, LVBench, MathVision, Minerva, MMLU-Pro, MMMU, MMMU-Pro, MMStar, MMVU, MotionBench, MuirBench, Multi-Challenge, OVBench, OVOBench, RefSpatialBench, SuperGPQA, TempCompass, TOMATO, TVBench, VideoMME w sub., VideoMMMU, VideoSimpleQA, VLMsAreBiased, ZEROBench), while Seed 2.0 Mini is better at 5 benchmarks (Hallusion Bench, OmniDocBench 1.5, PHYBench, SimpleVQA, VLMsAreBlind).

Seed 1.8 significantly outperforms across most benchmarks.

Wed Sep 09 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Seed 2.0 Mini costs less

For input processing, Seed 1.8 ($0.25/1M tokens) is 2.5x more expensive than Seed 2.0 Mini ($0.10/1M tokens).

For output processing, Seed 1.8 ($2.00/1M tokens) is 5.0x more expensive than Seed 2.0 Mini ($0.40/1M tokens).

In conclusion, Seed 1.8 is more expensive than Seed 2.0 Mini.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Sep 09 2026 • llm-stats.com
ByteDance
Seed 1.8
Input tokens$0.25
Output tokens$2.00
Best providerDeepinfra
ByteDance
Seed 2.0 Mini
Input tokens$0.10
Output tokens$0.40
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Both models have the same input context window of 256,000 tokens. Both models can generate responses up to 256,000 tokens.

ByteDance
Seed 1.8
Input256,000 tokens
Output256,000 tokens
ByteDance
Seed 2.0 Mini
Input256,000 tokens
Output256,000 tokens
Wed Sep 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Seed 1.8 and Seed 2.0 Mini support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Seed 1.8

Text
Images
Audio
Video

Seed 2.0 Mini

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Seed 1.8

Proprietary

Closed source

Seed 2.0 Mini

Proprietary

Closed source

Release Timeline

When each model was launched

Both models were released on 2026-02-17.

They likely represent similar generations of model development.

Seed 1.8

Feb 17, 2026

6 months ago

Seed 2.0 Mini

Feb 17, 2026

6 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Seed 1.8 is available from DeepInfra. Seed 2.0 Mini is available from DeepInfra.

Seed 1.8

deepinfra logo
Deepinfra
Input Price:Input: $0.25/1MOutput Price:Output: $2.00/1M

Seed 2.0 Mini

deepinfra logo
Deepinfra
Input Price:Input: $0.10/1MOutput Price:Output: $0.40/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Seed 1.8 and Seed 2.0 Mini side-by-side, then vote on the output you prefer.

Seed 1.8
✓ Preferred
Seed 2.0 Mini
Open in Playground

FAQ

Common questions about Seed 1.8 vs Seed 2.0 Mini.

Which is better, Seed 1.8 or Seed 2.0 Mini?

Seed 1.8 leads the LLM Stats Score 34.2 to 27.9. Seed 1.8 is made by ByteDance and Seed 2.0 Mini is made by ByteDance. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Seed 1.8 compare to Seed 2.0 Mini in benchmarks?

Seed 1.8 scores CountBench: 96.3%, AIME 2025: 94.3%, VLMsAreBlind: 93.0%, MMLU: 92.3%, AI2D: 89.1%. Seed 2.0 Mini scores CountBench: 95.5%, VLMsAreBlind: 93.1%, Graphwalks parents <128k: 93.0%, CharXiv-D: 91.9%, LongFact Concepts: 91.4%.

Is Seed 1.8 cheaper than Seed 2.0 Mini?

Seed 2.0 Mini is 2.5x cheaper for input tokens. Seed 1.8 costs $0.25/M input and $2.00/M output via deepinfra. Seed 2.0 Mini costs $0.10/M input and $0.40/M output via deepinfra.

What are the context window sizes for Seed 1.8 and Seed 2.0 Mini?

Seed 1.8 supports 256K tokens and Seed 2.0 Mini supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Seed 1.8 and Seed 2.0 Mini?

Key differences include LLM Stats Score (34.2 vs 27.9), input pricing ($0.25 vs $0.10/M). See the full comparison above for benchmark-by-benchmark results.