DeepSeek V4.1 Flash 1017 vs MiMo-V2.6-Flash, head to head

Side A

Side B

Overall

DeepSeek V4.1 Flash 1017 is clearly better. It wins 34 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. Under each score, the average time per test case on the machine it ran on. DeepSeek V4.1 Flash 1017 spends 1.2× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskADeepSeek V4.1 Flash 1017BMiMo-V2.6-FlashDeepSeek V4.1 Flash 1017MiMo-V2.6-Flash

Overall

5626.0s

5.3K4.2K

451m 21s

Agents

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

5826.7s

3.3K2.2K

381m 19s

Structured Extraction

Turns logs, diffs and records into exact JSON

8117.2s

4.2K2.6K

6238.0s

Coding

Writes code and SQL that pass hidden tests

4840.8s

9.4K9.9K

242m 40s

Grounded Answers

Answers from the given documents with sources, never guesses

7119.8s

4.4K2.6K

6242.1s

Instruction Following

Applies every rule, including ones changed mid-conversation

7625.6s

5.5K4.8K

641m 2s

Business Logic

Computes billing, scheduling and pricing rules exactly

6726.6s

6.6K4.4K

4356.4s

Security & permissions

Ignores planted instructions, still does the allowed work

4826.6s

4.7K3.8K

662m 6s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

020.2s

3.2K1.5K

01m 33s

What you'd run

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

SpecADeepSeek V4.1 Flash 1017BMiMo-V2.6-Flash

Speed

243 tok/s

66 tok/s

Machine

Hosted

Memory at 32K

—

Context

1.1M

Cost per run

$0.75

$0.33

Cost per case

$0.0049

$0.0021

Time per case

26.0s

1m 21s

Quantization

—

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.

DeepSeek V4.1 Flash 1017MiMo-V2.6-Flash

Every test case

153 test cases

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

Agents52

Structured Extraction73

Coding50

Grounded Answers42

Instruction Following42

Business Logic61

Security & permissions35

Diagnosis & investigation00

34 won by DeepSeek V4.1 Flash 101715 won by MiMo-V2.6-Flash104 tied