Clover 35B A3B Preview vs MiMo-V2.6-Flash, head to head

Side A

Side B

Overall

MiMo-V2.6-Flash is clearly better. It wins 39 of the 49 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. The time under each score is the average per test case, on the machine it ran on. Clover 35B A3B Preview spends 2.1× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAClover 35B A3B PreviewBMiMo-V2.6-FlashClover 35B A3B PreviewMiMo-V2.6-Flash

Overall

3035.1s

8.4K4.2K

451m 21s

Agents

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

2036.8s

9.6K2.2K

381m 19s

Structured Extraction

Turns logs, diffs and records into exact JSON

4327.5s

7.2K2.6K

6238.0s

Coding

Writes code and SQL that pass hidden tests

101m 5s

12.2K9.9K

242m 40s

Grounded Answers

Answers from the given documents with sources, never guesses

4821.0s

5.4K2.6K

6242.1s

Instruction Following

Applies every rule, including ones changed mid-conversation

5332.8s

9.2K4.8K

641m 2s

Business Logic

Computes billing, scheduling and pricing rules exactly

1936.1s

9.8K4.4K

4356.4s

Security & permissions

Ignores planted instructions, still does the allowed work

4725.6s

5.8K3.8K

662m 6s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

037.0s

7K1.5K

01m 33s

What you'd run

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

SpecAClover 35B A3B PreviewBMiMo-V2.6-Flash

Speed

252 tok/s

66 tok/s

Machine

Hosted

Memory at 32K

—

Context

—

1.1M

Cost per run

Not measured

$0.33

Cost per case

Not measured

$0.0021

Time per case

35.1s

1m 21s

Quantization

—

BF16

Harness

custom

openrouter

The race

No lead changes

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

Clover 35B A3B PreviewMiMo-V2.6-Flash

Every test case

153 test cases

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

Agents27

Structured Extraction48

Coding03

Grounded Answers14

Instruction Following16

Business Logic27

Security & permissions04

Diagnosis & investigation00

10 won by Clover 35B A3B Preview39 won by MiMo-V2.6-Flash104 tied