Flint vs Mistral Large 4, head to head

Side A

Side B

Overall

Mistral Large 4 is clearly better. It wins 29 of the 44 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. Flint spends 2.2× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAFlintBMistral Large 4FlintMistral Large 4

Overall

211m 17s

10.9K6.2K

281m 56s

Agents

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

1447.7s

4.8K795

1126.1s

Structured Extraction

Turns logs, diffs and records into exact JSON

291m 17s

10.9K288

153.78s

Coding

Writes code and SQL that pass hidden tests

141m 19s

12K9.3K

332m 48s

Grounded Answers

Answers from the given documents with sources, never guesses

2957.7s

8.7K8.1K

382m 45s

Instruction Following

Applies every rule, including ones changed mid-conversation

352m 28s

22.2K12.9K

693m 47s

Business Logic

Computes billing, scheduling and pricing rules exactly

101m 20s

11.7K8.8K

242m 40s

Security & permissions

Ignores planted instructions, still does the allowed work

3552.6s

7.1K3.7K

331m 9s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

057.0s

7.3K4.4K

01m 19s

What you'd run

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

SpecAFlintBMistral Large 4

Speed

149 tok/s

56 tok/s

Machine

Hosted

Memory at 32K

—

Context

256K

512K

Cost per run

Not measured

$2.67

Cost per case

Not measured

$0.017

Time per case

1m 17s

1m 56s

Quantization

BF16

—

Harness

openrouter

The race

5 lead changes

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

FlintMistral Large 4

Every test case

153 test cases

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

Agents23

Structured Extraction51

Coding38

Grounded Answers13

Instruction Following18

Business Logic03

Security & permissions33

Diagnosis & investigation00

15 won by Flint29 won by Mistral Large 4109 tied