Beam 1.0 501B A23B vs MiMo-V2.6-Pro, head to head

Side A

Side B

Overall

Too close to call. Beam 1.0 501B A23B wins 33 of the 57 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. MiMo-V2.6-Pro spends 1.5× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskABeam 1.0 501B A23BBMiMo-V2.6-ProBeam 1.0 501B A23BMiMo-V2.6-Pro

Overall

5717.2s

4K5.9K

482m 13s

Agents

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

5521.8s

4.8K8.7K

474m 48s

Structured Extraction

Turns logs, diffs and records into exact JSON

819.98s

3.4K3.4K

601m 26s

Coding

Writes code and SQL that pass hidden tests

4819.9s

4.5K10.7K

242m 58s

Grounded Answers

Answers from the given documents with sources, never guesses

6911.6s

2.7K3.2K

621m 9s

Instruction Following

Applies every rule, including ones changed mid-conversation

7820.9s

5.6K4.5K

591m 23s

Business Logic

Computes billing, scheduling and pricing rules exactly

5714.0s

4.2K7.1K

571m 52s

Security & permissions

Ignores planted instructions, still does the allowed work

5120.6s

3.2K3.6K

711m 41s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

1724.3s

3.1K6.2K

02m 54s

What you'd run

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

SpecABeam 1.0 501B A23BBMiMo-V2.6-Pro

Speed

274 tok/s

55 tok/s

Machine

Hosted

Memory at 32K

—

Context

1.1M

Cost per run

$0.83

$1.80

Cost per case

$0.0054

$0.012

Time per case

17.2s

2m 13s

Quantization

FP8

BF16

Harness

openrouter

The race

1 lead change

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

Beam 1.0 501B A23BMiMo-V2.6-Pro

Every test case

153 test cases

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

Agents44

Structured Extraction72

Coding71

Grounded Answers43

Instruction Following62

Business Logic33

Security & permissions19

Diagnosis & investigation10

33 won by Beam 1.0 501B A23B24 won by MiMo-V2.6-Pro96 tied