modelbenchmark.io

deepseek-r1-0528-distill-qwen3-8b

DeepSeek · deepseek-r1-0528-distill-qwen3-8b

Compare

Specification

most-agreed values

Context
131K
Max output
131K
Released
Knowledge cutoff
Retires
Open weights
Input
Output

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.20

Quality

3 benchmarks · 1 source

Composite
16th
percentile of 334 scored models
Rank
281 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning2nd2/4 bench
math42nd1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202543.9 ±6.8defaultEpoch AI2026-08-28
Chess Puzzles3.0 ±1.7defaultEpoch AI2026-08-28
GPQA diamond9.3 ±1.1defaultEpoch AI2026-08-28

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks_ai$0.20$0.20131K131K

More from DeepSeek

most-hosted first