DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
starter@v1HostedOpenRouterserved by MorphFP81M context2026-10-03 09:34 UTC64
102 of 153 test cases fully passed
31.8tok/s
Mean per test case, 30 tok/s over the run
6Ktokens
Answer plus reasoning
5.4Ktokens
91% of the output
2.4M
1.4M in, 917.3K out
9h 8m
3m 35s per caseSum of request times
$0.39
$0.0026 per caseAt the provider's list price
Every test case
One square per test case. Select a square to read the answer.
46Agents9 of 21 passed
86Structured Extraction18 of 21 passed
51Coding10 of 21 passed
76Grounded Answers16 of 21 passed
89Instruction Following18 of 21 passed
81Business Logic17 of 21 passed
69Security & permissions13 of 21 passed
17Diagnosis & investigation1 of 6 passed
Speed and output per test case
One bar per test case. Hover a bar to see its numbers. Select it to read the answer.
Peak 64 tok/s
ReasoningAnswer
Test by test
Every answer with its reasoning and the checks it had to pass.
Reproduce this run
The prompts stay private so models can't train on them. The hashes pin the exact suite and config this run used.
OpenRouterHosted
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","provider":{"order":["morph/fp8"],"allow_fallbacks":false},"messages":[{"role":"user","content":"Hello"}]}'The request the benchmark sent, pinned to the provider that served it.
Configuration
Where the suite ran, and the token budget each task got.
- Hosted
- OpenRouter
- Morph
- FP8
- 1M
- 0
- v1.0.0
- 2026-10-03 09:34 UTC
{
"provider": {
"order": [
"morph/fp8"
],
"allow_fallbacks": false
}
}| Task | Reasoning | Max output per call |
|---|---|---|
| Agents | 4.1K | 12.3K |
| Structured Extraction | 4.1K | 12.3K |
| Coding | 4.1K | 12.3K |
| Grounded Answers | 4.1K | 12.3K |
| Instruction Following | 4.1K | 12.3K |
| Business Logic | 4.1K | 12.3K |
| Security & permissions | 4.1K | 12.3K |
| Diagnosis & investigation | 4.1K | 12.3K |