LFM2.5 24B A2B vs Underdog Saluki 27B, head to head

Side A

Side B

Overall

Underdog Saluki 27B is clearly better. It wins 54 of the 56 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 1.5× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskALFM2.5 24B A2BBUnderdog Saluki 27BLFM2.5 24B A2BUnderdog Saluki 27B

Overall

71m 53s

9.2K6.9K

335m 15s

Agents

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

123m 49s

18.5K11.8K

409m 2s

Structured Extraction

Turns logs, diffs and records into exact JSON

1054.9s

4.4K4.4K

433m 17s

Coding

Writes code and SQL that pass hidden tests

11m 15s

6.1K9.2K

166m 54s

Grounded Answers

Answers from the given documents with sources, never guesses

557.8s

4.7K4.5K

433m 22s

Instruction Following

Applies every rule, including ones changed mid-conversation

162m 44s

13.4K8K

466m 5s

Business Logic

Computes billing, scheduling and pricing rules exactly

51m 2s

5K5.2K

333m 55s

Security & permissions

Ignores planted instructions, still does the allowed work

101m 52s

9K4.9K

433m 47s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

04m 12s

19.9K8.7K

06m 39s

What you'd run

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

SpecALFM2.5 24B A2BBUnderdog Saluki 27B

Speed

82 tok/s

23 tok/s

Machine

Apple M5 Pro, 48 GB

Memory at 32K

25.0 GB

10.2 GB

Context

128K

256K

Cost per run

Not measured

Cost per case

Not measured

Time per case

1m 53s

5m 15s

Quantization

Q8_0

IQ2_XS

Harness

llama.cpp

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 A2BUnderdog Saluki 27B

Every test case

153 test cases

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

Agents19

Structured Extraction07

Coding17

Grounded Answers08

Instruction Following09

Business Logic06

Security & permissions08

Diagnosis & investigation00

2 won by LFM2.5 24B A2B54 won by Underdog Saluki 27B97 tied