GLM 5.3 Flash vs MiMo-V2.6-Pro, head to head

Side A

Side B

Overall

MiMo-V2.6-Pro is clearly better. It wins 44 of the 66 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 2.1× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAGLM 5.3 FlashBMiMo-V2.6-ProGLM 5.3 FlashMiMo-V2.6-Pro

Overall

3555.5s

2.8K5.9K

482m 13s

Agents

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

1037.0s

6078.7K

474m 48s

Structured Extraction

Turns logs, diffs and records into exact JSON

4847.2s

2.7K3.4K

601m 26s

Coding

Writes code and SQL that pass hidden tests

541m 52s

5.3K10.7K

242m 58s

Grounded Answers

Answers from the given documents with sources, never guesses

3756.8s

2.9K3.2K

621m 9s

Instruction Following

Applies every rule, including ones changed mid-conversation

4340.8s

2K4.5K

591m 23s

Business Logic

Computes billing, scheduling and pricing rules exactly

331m 18s

5.8K7.1K

571m 52s

Security & permissions

Ignores planted instructions, still does the allowed work

5525.2s

9633.6K

711m 41s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

027.0s

5636.2K

02m 54s

What you'd run

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

SpecAGLM 5.3 FlashBMiMo-V2.6-Pro

Speed

60 tok/s

55 tok/s

Machine

Hosted

Memory at 32K

—

Context

1.1M

Cost per run

$0.19

$1.80

Cost per case

$0.0013

$0.012

Time per case

55.5s

2m 13s

Quantization

FP8

BF16

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.

GLM 5.3 FlashMiMo-V2.6-Pro

Every test case

153 test cases

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

Agents08

Structured Extraction47

Coding102

Grounded Answers27

Instruction Following37

Business Logic38

Security & permissions05

Diagnosis & investigation00

22 won by GLM 5.3 Flash44 won by MiMo-V2.6-Pro87 tied