whatmodel.sh / Seed2.0 Lite
Seed2.0 Lite
↗ share
+ contribute
Seed2.0 Lite is a closed-weights language model from ByteDance Seed. Licence: proprietary.
Catalogue identity notes
Comparison-only. ByteDance Seed's Seed2.0 Lite, one of the three sizes (Pro / Lite / Mini) of the Seed2.0 series described in its model card (arXiv 2607.00248v1, submitted 2026-06-30), which lists its Volcengine price per 1M tokens. Added so the card's own tau2-telecom figures for Seed2.0 Pro (catalogue dola-seed-2-0-pro) and Lite form a two-model ByteDance run. Release month not printed in the card (omitted).
$ how it compares
The LLMs ranked either side of Seed2.0 Lite, out of 1132 with a score, then more from ByteDance Seed.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 64 | 73±4 | local | |||
| 65 | 73±2 | api $1.56/M | |||
| 66 | 73±4 | comparison only | |||
| 67 | 73±1 | api $1.71/M +local | |||
| 68 | 73±3 | comparison only | |||
| more from ByteDance Seed | |||||
| 60 | 74±3 | comparison only | |||
| 235 | 63±1 | local | |||
$ what it's good at
agent tasks█··········█ #2 of 2 * · 95% of its score · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| τ²-bench Telecom lab | 92.1% ✎ | ▁·▅█▆▅▂▃▃▂▃▁ beats 69/89 | 95% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · ByteDance Seed - Seed2.0 Mode… 95%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
| 1 | 95% | |
| prior · pull toward the middle | 5% | |
| weighted average | = 73.0 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json