LFM2.5 24B A2B vs Ling 3.1 Flash, head to head

Side A

Side B

Overall

Ling 3.1 Flash is clearly better. It wins 69 of the 71 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 A2BBLing 3.1 FlashLFM2.5 24B A2BLing 3.1 Flash

Overall

71m 53s

9.2K7.9K

451m 16s

Agents

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

123m 49s

18.5K4.5K

4155.9s

Structured Extraction

Turns logs, diffs and records into exact JSON

1054.9s

4.4K8.1K

711m 11s

Coding

Writes code and SQL that pass hidden tests

11m 15s

6.1K11.3K

241m 42s

Grounded Answers

Answers from the given documents with sources, never guesses

557.8s

4.7K6.7K

5258.9s

Instruction Following

Applies every rule, including ones changed mid-conversation

162m 44s

13.4K11.4K

761m 55s

Business Logic

Computes billing, scheduling and pricing rules exactly

51m 2s

5K9.7K

381m 22s

Security & permissions

Ignores planted instructions, still does the allowed work

101m 52s

9K5.2K

5456.1s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

04m 12s

19.9K3.2K

042.1s

What you'd run

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

SpecALFM2.5 24B A2BBLing 3.1 Flash

Speed

82 tok/s

112 tok/s

Machine

Apple M5 Pro, 48 GB

Hosted

Memory at 32K

25.0 GB

—

Context

128K

256K

Cost per run

Not measured

Cost per case

Not measured

Time per case

1m 53s

1m 16s

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 A2BLing 3.1 Flash

Every test case

153 test cases

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

Agents18

Structured Extraction013

Coding15

Grounded Answers010

Instruction Following016

Business Logic07

Security & permissions010

Diagnosis & investigation00

2 won by LFM2.5 24B A2B69 won by Ling 3.1 Flash82 tied