Apodex 1.1 Mini (free) vs Beam 1.0 501B A23B, head to head

Side A

Side B

Overall

Beam 1.0 501B A23B is clearly better. It wins 63 of the 69 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. Apodex 1.1 Mini (free) spends 1.8× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAApodex 1.1 Mini (free)BBeam 1.0 501B A23BApodex 1.1 Mini (free)Beam 1.0 501B A23B

Overall

2535.1s

8.5K4K

5717.2s

Agents

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

2639.4s

6.2K4.8K

5521.8s

Structured Extraction

Turns logs, diffs and records into exact JSON

5227.2s

7.7K3.4K

819.98s

Coding

Writes code and SQL that pass hidden tests

446.5s

12.1K4.5K

4819.9s

Grounded Answers

Answers from the given documents with sources, never guesses

2926.0s

6.9K2.7K

6911.6s

Instruction Following

Applies every rule, including ones changed mid-conversation

3644.5s

11.4K5.6K

7820.9s

Business Logic

Computes billing, scheduling and pricing rules exactly

1435.4s

10K4.2K

5714.0s

Security & permissions

Ignores planted instructions, still does the allowed work

4027.3s

5.8K3.2K

5120.6s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

034.6s

5.1K3.1K

1724.3s

What you'd run

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

SpecAApodex 1.1 Mini (free)BBeam 1.0 501B A23B

Speed

278 tok/s

274 tok/s

Machine

Hosted

Memory at 32K

—

Context

256K

Cost per run

Not measured

$0.83

Cost per case

Not measured

$0.0054

Time per case

35.1s

17.2s

Quantization

BF16

FP8

Harness

openrouter

The race

No lead changes

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

Apodex 1.1 Mini (free)Beam 1.0 501B A23B

Every test case

153 test cases

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

Agents19

Structured Extraction17

Coding010

Grounded Answers09

Instruction Following012

Business Logic09

Security & permissions46

Diagnosis & investigation01

6 won by Apodex 1.1 Mini (free)63 won by Beam 1.0 501B A23B84 tied