Benchmark Almanac

Seed-Thinking-v1.5

Seed-Thinking-v1.5.

ByteDance Seed Released April 10th, 2025 Family Seed 1 The lab's model card Compare with others
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
ByteDance Seed Apr 2025

Seed-Thinking-v1.5

Closed weights Flagship

134.1 #236 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • SuperGPQA 62.1% #18 /35
  • LiveCodeBench v5 64.9% #18 /47
  • MMLU-Pro 87% #10 /167

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.

Knowledge and language

BenchmarkScoreRankSource
MMLU-Pro 87% #10 of 167 Lab model card
IFEval 87.4% #60 of 135 Lab model card
COLLIE 73.1% #6 of 12 Lab model card
SuperGPQA 62.1% #18 of 35 Lab model card
SimpleQA 12.9% #46 of 60 Lab model card

Math and science

BenchmarkScoreRankSource
PolyMath 47.2% #4 of 38 Official leaderboard
AIME 2024 86.7% #28 of 88 Lab model card
GPQA Diamond 77.3% #133 of 302 Lab model card
AIME 2025 74% #103 of 143 Lab model card
Beyond AIME 48% #12 of 14 Lab model card
ARC-AGI 39.9% #21 of 21 Lab model card

Coding

BenchmarkScoreRankSource
LiveCodeBench v5 64.9% #18 of 47 Lab model card
Aider Polyglot 54.2% #17 of 30 Lab model card
SWE-bench Verified 47% #135 of 155 Lab model card

Its lab's numbers put it at 134.1, number 236 of 404

The Self-Reported Index fits one score to the 13 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 131.8 to 136.4. How we compute it.

Its lab's number next to a leaderboard

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap
MMLU-Pro 87% MMLU-PRO 87% Leaderboard Same

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.