DeepSeek V4.1 Flash 1017 vs Claude Haiku 5.5, head to head

Side A

Side B

Overall

Claude Haiku 5.5 is clearly better. It wins 32 of the 42 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. DeepSeek V4.1 Flash 1017 spends 1.6× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskADeepSeek V4.1 Flash 1017BClaude Haiku 5.5DeepSeek V4.1 Flash 1017Claude Haiku 5.5

Overall

5626.0s

5.3K3.9K

7025.5s

Agents

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

5826.7s

3.3K3.7K

6139.5s

Structured Extraction

Turns logs, diffs and records into exact JSON

8117.2s

4.2K2.6K

9013.5s

Coding

Writes code and SQL that pass hidden tests

4840.8s

9.4K6.8K

8630.6s

Grounded Answers

Answers from the given documents with sources, never guesses

7119.8s

4.4K2.2K

7613.9s

Instruction Following

Applies every rule, including ones changed mid-conversation

7625.6s

5.5K4.3K

9431.5s

Business Logic

Computes billing, scheduling and pricing rules exactly

6726.6s

6.6K5.5K

6726.0s

Security & permissions

Ignores planted instructions, still does the allowed work

4826.6s

4.7K2.7K

6723.4s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

020.2s

3.2K2.3K

1725.5s

What you'd run

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

SpecADeepSeek V4.1 Flash 1017BClaude Haiku 5.5

Speed

243 tok/s

225 tok/s

Machine

Hosted

Memory at 32K

—

Context

Cost per run

$0.75

$0.42

Cost per case

$0.0049

$0.0028

Time per case

26.0s

25.5s

Quantization

—

Harness

openrouter

The race

4 lead changes

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

DeepSeek V4.1 Flash 1017Claude Haiku 5.5

Every test case

153 test cases

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

Agents23

Structured Extraction13

Coding08

Grounded Answers23

Instruction Following05

Business Logic33

Security & permissions26

Diagnosis & investigation01

10 won by DeepSeek V4.1 Flash 101732 won by Claude Haiku 5.5111 tied