Flint vs LFM2.5 24B A2B, head to head

Side A

Side B

Overall

Flint is clearly better. It wins 29 of the 34 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. Both models spend about the same on thinking per test case.

Thinking tokensAnswer tokens

TaskAFlintBLFM2.5 24B A2BFlintLFM2.5 24B A2B

Overall

211m 17s

10.9K9.2K

71m 53s

Agents

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

1447.7s

4.8K18.5K

123m 49s

Structured Extraction

Turns logs, diffs and records into exact JSON

291m 17s

10.9K4.4K

1054.9s

Coding

Writes code and SQL that pass hidden tests

141m 19s

12K6.1K

11m 15s

Grounded Answers

Answers from the given documents with sources, never guesses

2957.7s

8.7K4.7K

557.8s

Instruction Following

Applies every rule, including ones changed mid-conversation

352m 28s

22.2K13.4K

162m 44s

Business Logic

Computes billing, scheduling and pricing rules exactly

101m 20s

11.7K5K

51m 2s

Security & permissions

Ignores planted instructions, still does the allowed work

3552.6s

7.1K9K

101m 52s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

057.0s

7.3K19.9K

04m 12s

What you'd run

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

SpecAFlintBLFM2.5 24B A2B

Speed

149 tok/s

82 tok/s

Machine

Hosted

Apple M5 Pro, 48 GB

Memory at 32K

—

25.0 GB

Context

256K

128K

Cost per run

Not measured

Cost per case

Not measured

Time per case

1m 17s

1m 53s

Quantization

BF16

Q8_0

Harness

openrouter

llama.cpp

The race

2 lead changes

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

FlintLFM2.5 24B A2B

Every test case

153 test cases

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

Agents31

Structured Extraction40

Coding32

Grounded Answers50

Instruction Following61

Business Logic10

Security & permissions71

Diagnosis & investigation00

29 won by Flint5 won by LFM2.5 24B A2B119 tied