[mle]/DaBench
Leaderboard

DeepSeek V4.1 Flash 1017

deepseek/deepseek-v4.1-flash-1017

Hosteddeepseek243 tok/sopenrouterserved by DeepSeek1M context
Run recordCompare
Overall score
56

89 of 153 test cases fully passed

What it built

What it wrote for showcase prompts, running live in your browser.

Scores by task

Scores give partial credit. Passed counts fully correct answers only. Select a task to read its test cases.

  1. 58Agents9 of 21 passedp90 latency 54.0s
  2. 81Structured Extraction17 of 21 passedp90 latency 36.3s
  3. 48Coding10 of 21 passedp90 latency 1m 2s
  4. 71Grounded Answers15 of 21 passedp90 latency 36.8s
  5. 76Instruction Following14 of 21 passedp90 latency 46.2s
  6. 67Business Logic14 of 21 passedp90 latency 51.5s
  7. 48Security & permissions10 of 21 passedp90 latency 1m 4s
  8. 0Diagnosis & investigation0 of 6 passedp90 latency 42.0s

Run it yourself

The API call the benchmark made, and the settings behind this score.

Deployment
Hosted
API
OpenRouter
Serving provider
DeepSeek
Precision
Provider default
Context window
1M
Throughput
243 tok/s
Cost of a suite run
$0.75
Cost per case
$0.0049
Time per case
26.0s
Measured
2026-10-17
Run this buildOpenRouterHosted
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4.1-flash-1017","provider":{"order":["deepseek"],"allow_fallbacks":false},"service_tier":"default","messages":[{"role":"user","content":"Hello"}]}'

The request the benchmark sent, pinned to the provider that served it.

Watch the test

Video tests of this model on coding and agent work.

DeepSeek V4.1 Flash First Test | Better V4 Flash? | Coding with OpenCode, Frontend & Agentic Work11 Sep 2026

One email when a new model lands on the board or in the showcase. Unsubscribe anytime.

LeaderboardCompare DeepSeek V4.1 Flash 1017 with another model