Claude Haiku 5.5 vs Underdog Saluki 27B, head to head

Side A

Side B

Overall

Claude Haiku 5.5 is clearly better. It wins 65 of the 67 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 1.9× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAClaude Haiku 5.5BUnderdog Saluki 27BClaude Haiku 5.5Underdog Saluki 27B

Overall

7025.5s

3.9K6.9K

335m 15s

Agents

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

6139.5s

3.7K11.8K

409m 2s

Structured Extraction

Turns logs, diffs and records into exact JSON

9013.5s

2.6K4.4K

433m 17s

Coding

Writes code and SQL that pass hidden tests

8630.6s

6.8K9.2K

166m 54s

Grounded Answers

Answers from the given documents with sources, never guesses

7613.9s

2.2K4.5K

433m 22s

Instruction Following

Applies every rule, including ones changed mid-conversation

9431.5s

4.3K8K

466m 5s

Business Logic

Computes billing, scheduling and pricing rules exactly

6726.0s

5.5K5.2K

333m 55s

Security & permissions

Ignores planted instructions, still does the allowed work

6723.4s

2.7K4.9K

433m 47s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

1725.5s

2.3K8.7K

06m 39s

What you'd run

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

SpecAClaude Haiku 5.5BUnderdog Saluki 27B

Speed

225 tok/s

23 tok/s

Machine

Hosted

Apple M5 Pro, 48 GB

Memory at 32K

—

10.2 GB

Context

256K

Cost per run

$0.42

Not measured

Cost per case

$0.0028

Not measured

Time per case

25.5s

5m 15s

Quantization

—

IQ2_XS

Harness

openrouter

llama.cpp

The race

1 lead change

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

Claude Haiku 5.5Underdog Saluki 27B

Every test case

153 test cases

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

Agents60

Structured Extraction100

Coding170

Grounded Answers70

Instruction Following100

Business Logic81

Security & permissions61

Diagnosis & investigation10

65 won by Claude Haiku 5.52 won by Underdog Saluki 27B86 tied