Beam 1.0 501B A23B vs LFM2.5 24B A2B, head to head

Side A

Side B

Overall

Beam 1.0 501B A23B is clearly better. It wins 90 of the 91 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 2.4× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskABeam 1.0 501B A23BBLFM2.5 24B A2BBeam 1.0 501B A23BLFM2.5 24B A2B

Overall

5717.2s

4K9.2K

71m 53s

Agents

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

5521.8s

4.8K18.5K

123m 49s

Structured Extraction

Turns logs, diffs and records into exact JSON

819.98s

3.4K4.4K

1054.9s

Coding

Writes code and SQL that pass hidden tests

4819.9s

4.5K6.1K

11m 15s

Grounded Answers

Answers from the given documents with sources, never guesses

6911.6s

2.7K4.7K

557.8s

Instruction Following

Applies every rule, including ones changed mid-conversation

7820.9s

5.6K13.4K

162m 44s

Business Logic

Computes billing, scheduling and pricing rules exactly

5714.0s

4.2K5K

51m 2s

Security & permissions

Ignores planted instructions, still does the allowed work

5120.6s

3.2K9K

101m 52s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

1724.3s

3.1K19.9K

04m 12s

What you'd run

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

SpecABeam 1.0 501B A23BBLFM2.5 24B A2B

Speed

274 tok/s

82 tok/s

Machine

Hosted

Apple M5 Pro, 48 GB

Memory at 32K

—

25.0 GB

Context

128K

Cost per run

$0.83

Not measured

Cost per case

$0.0054

Not measured

Time per case

17.2s

1m 53s

Quantization

FP8

Q8_0

Harness

openrouter

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.

Beam 1.0 501B A23BLFM2.5 24B A2B

Every test case

153 test cases

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

Agents110

Structured Extraction150

Coding100

Grounded Answers140

Instruction Following160

Business Logic110

Security & permissions121

Diagnosis & investigation10

90 won by Beam 1.0 501B A23B1 won by LFM2.5 24B A2B62 tied