Benchmark Almanac

Seed-Coder-8B-Instruct

Seed-Coder-8B-Instruct.

ByteDance Seed Released May 8th, 2025 Family Seed-Coder The lab's model card Compare with others
16
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
ByteDance Seed May 2025

Seed-Coder-8B-Instruct

Open weights Small

123.0 #329 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • BigCodeBench 53.3% #4 /14
  • FullStackBench 55.8% #8 /8
  • AutoCodeBench 32.3% #27 /34

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Coding

BenchmarkScoreRankSource
MBPP 85.2% #11 of 71 Lab model card
BigCodeBench 53.3% #4 of 14 Lab model card
HumanEval 84.8% #44 of 101 Lab model card
NaturalCodeBench 49.6% #1 of 2 Lab model card
MBPP+ 71.2% #10 of 15 Lab model card
MBXP 75.3% #2 of 3 Lab model card
HumanEval+ 78.7% #20 of 27 Lab model card
AutoCodeBench 32.3% #27 of 34 Official leaderboard
Aider-Edit 57.1% #4 of 5 Lab model card
ArtifactsBench (Gemini 2.5 Pro 0506 judge) 35.2% #15 of 18 Official leaderboard
SWE-bench Verified 19.2% #153 of 155 Lab model card
FullStackBench 55.8% #8 of 8 Lab model card
BigCodeBench-Hard 26.4% #3 of 3 Lab model card
CanItEdit 50.5% #3 of 3 Lab model card
Multi-SWE-bench mini 4.00% #2 of 2 Lab model card
MHPP 36.2% #1 of 1 Lab model card

Its lab's numbers put it at 123.0, number 329 of 404

The Self-Reported Index fits one score to the 7 capability results ByteDance Seed reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 118.5 to 127.5. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 11 of them aren't in the launch post.