LFM2.5 24B A2B vs Claude Haiku 5.5, head to head

Side A

Side B

Overall

Claude Haiku 5.5 is clearly better. It wins 109 of the 111 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. LFM2.5 24B A2B spends 2.8× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskALFM2.5 24B A2BBClaude Haiku 5.5LFM2.5 24B A2BClaude Haiku 5.5

Overall

71m 53s

9.2K3.9K

7025.5s

Agents

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

123m 49s

18.5K3.7K

6139.5s

Structured Extraction

Turns logs, diffs and records into exact JSON

1054.9s

4.4K2.6K

9013.5s

Coding

Writes code and SQL that pass hidden tests

11m 15s

6.1K6.8K

8630.6s

Grounded Answers

Answers from the given documents with sources, never guesses

557.8s

4.7K2.2K

7613.9s

Instruction Following

Applies every rule, including ones changed mid-conversation

162m 44s

13.4K4.3K

9431.5s

Business Logic

Computes billing, scheduling and pricing rules exactly

51m 2s

5K5.5K

6726.0s

Security & permissions

Ignores planted instructions, still does the allowed work

101m 52s

9K2.7K

6723.4s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

04m 12s

19.9K2.3K

1725.5s

What you'd run

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

SpecALFM2.5 24B A2BBClaude Haiku 5.5

Speed

82 tok/s

225 tok/s

Machine

Apple M5 Pro, 48 GB

Hosted

Memory at 32K

25.0 GB

—

Context

128K

Cost per run

Not measured

$0.42

Cost per case

Not measured

$0.0028

Time per case

1m 53s

25.5s

Quantization

Q8_0

—

Harness

llama.cpp

openrouter

The race

No lead changes

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

LFM2.5 24B A2BClaude Haiku 5.5

Every test case

153 test cases

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

Agents012

Structured Extraction017

Coding118

Grounded Answers015

Instruction Following019

Business Logic013

Security & permissions114

Diagnosis & investigation01

2 won by LFM2.5 24B A2B109 won by Claude Haiku 5.542 tied