Seed 2.0 Lite: benchmark results

ByteDance's lightweight Seed 2.0 tier. Provider: ByteDance. Released 2026-02-16. Access: API.

Unified ELO 1632 ± 1, rank #176 of 1392 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Beyond Function Calling51.3Overall (self-reported)100
ClawProBench60.4Final Score (self-reported)80.4
PinchBench89.71Success Rate (%)77.6
ZeroEval GPQA Diamond85.1GPQA Diamond Score75.4
Equational Theories Benchmark64.5F1 (%, mean of six settings)75
AI Chess Leaderboard (Continuation)819Elo73.3
LLM Stats Score32.09LLM Stats Score (conservative rating)72.1
AI Chess Leaderboard (Reasoning)847Elo69.8
OpenClawProBench66.1Overall Score (%)60.6
Wolfram LLM Benchmarking Project43.6Correct Functionality (%)54.5
FutureX36.17Overall Score (latest week, %)53.8
PerfCodeBench60.19CGRE (self-reported)47.4

Interactive version: theaggregate.ai/model?slug=seed-2-0-lite · How It Works · Data refreshed daily, snapshot 2026-09-05.