DeepSeek V4.1 Flash 1017 vs Underdog Saluki 27B, head to head

Side A

Side B

Overall

DeepSeek V4.1 Flash 1017 is clearly better. It wins 52 of the 65 test cases where they differ.

Learn to build evals like this in the AI Engineering Academy

Task by task

A score turns orange only when that model wins clearly more of the task's test cases. Under each score, the average time per test case on the machine it ran on. Underdog Saluki 27B spends 1.2× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskADeepSeek V4.1 Flash 1017BUnderdog Saluki 27BDeepSeek V4.1 Flash 1017Underdog Saluki 27B

Overall

5626.0s

5.3K6.9K

335m 15s

Agents

Runs multi-step jobs through tools, within a written policy

5826.7s

3.3K11.8K

409m 2s

Structured Extraction

Turns logs, diffs and records into exact JSON

8117.2s

4.2K4.4K

433m 17s

Coding

Writes code and SQL that pass hidden tests

4840.8s

9.4K9.2K

166m 54s

Grounded Answers

Answers from the given documents with sources, never guesses

7119.8s

4.4K4.5K

433m 22s

Instruction Following

Applies every rule, including ones changed mid-conversation

7625.6s

5.5K8K

466m 5s

Business Logic

Computes billing, scheduling and pricing rules exactly

6726.6s

6.6K5.2K

333m 55s

Security & permissions

Ignores planted instructions, still does the allowed work

4826.6s

4.7K4.9K

433m 47s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

020.2s

3.2K8.7K

06m 39s

What you'd run

The build behind each score. Orange marks the faster, smaller, cheaper or longer-context side.

SpecADeepSeek V4.1 Flash 1017BUnderdog Saluki 27B

Speed

243 tok/s

23 tok/s

Machine

Hosted

Apple M5 Pro, 48 GB

Memory at 32K

—

10.2 GB

Context

256K

Cost per run

$0.75

Not measured

Cost per case

$0.0049

Not measured

Time per case

26.0s

5m 15s

Quantization

—

IQ2_XS

Harness

openrouter

llama.cpp

The race

3 lead changes

Each model's running score as the test cases go by. The dashed line is a perfect run.

DeepSeek V4.1 Flash 1017Underdog Saluki 27B

Every test case

153 test cases

Each square is one test case, colored by the model that scored higher.

Agents83

Structured Extraction91

Coding92

Grounded Answers60

Instruction Following83

Business Logic92

Security & permissions32

Diagnosis & investigation00

52 won by DeepSeek V4.1 Flash 101713 won by Underdog Saluki 27B88 tied