← LLM

Baseten

DeepSeek-V4-Flash-0731

Measured 2026-10-04

Run DeepSeek-V4-Flash-0731 on Speko →

One API, every model on this board.

Score

83

Task done

93.16%

83–100% 95% CI bootstrap over items · n=95 · measured 2026-10-04

Refusal quality

72.2%

names the gap 57% · offers a route 67% · 10 probes x 3 iterations

Fabrication

0%

0 of 10 probes (30 probe runs) · ≤31%

Dead-air

36.8%

116 of 315 turns

Tool silence

53.2%

116 of 218 tool-call turns

Stalled

3.3%

3 of 90 runs

TTFT p50

558ms

558–1026 p50–p90 · n=38

Cost / 1M tok

$0.26

Share this result

Embed the live badge

Speko llm rank
Markdown
[![Speko llm rank](https://benchmarks.speko.ai/badge/llm/baseten-deepseek-v4-flash-0731.svg)](https://benchmarks.speko.ai/llm/baseten-deepseek-v4-flash-0731)
HTML
<a href="https://benchmarks.speko.ai/llm/baseten-deepseek-v4-flash-0731"><img src="https://benchmarks.speko.ai/badge/llm/baseten-deepseek-v4-flash-0731.svg" alt="Speko llm rank"></a>
URL
https://benchmarks.speko.ai/llm/baseten-deepseek-v4-flash-0731