Flint vs Spark X2.6 4B, head to head

Side A

Side B

Overall

Flint is clearly better. It wins 26 of the 40 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 1.4× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAFlintBSpark X2.6 4BFlintSpark X2.6 4B

Overall

211m 17s

10.9K8.2K

151m 3s

Agents

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

1447.7s

4.8K11.5K

141m 32s

Structured Extraction

Turns logs, diffs and records into exact JSON

291m 17s

10.9K5.3K

1039.5s

Coding

Writes code and SQL that pass hidden tests

141m 19s

12K9.1K

41m 8s

Grounded Answers

Answers from the given documents with sources, never guesses

2957.7s

8.7K6.6K

1050.2s

Instruction Following

Applies every rule, including ones changed mid-conversation

352m 28s

22.2K11.9K

371m 29s

Business Logic

Computes billing, scheduling and pricing rules exactly

101m 20s

11.7K4.9K

1036.3s

Security & permissions

Ignores planted instructions, still does the allowed work

3552.6s

7.1K7K

3154.3s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

057.0s

7.3K11.6K

01m 30s

What you'd run

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

SpecAFlintBSpark X2.6 4B

Speed

149 tok/s

136 tok/s

Machine

Hosted

RTX 5090, 32 GB

Memory at 32K

—

9.4 GB

Context

256K

605K

Cost per run

Not measured

$1.61 est.

Cost per case

Not measured

$0.011 est.

Time per case

1m 17s

1m 3s

Quantization

BF16

Harness

openrouter

llama.cpp

The race

4 lead changes

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

FlintSpark X2.6 4B

Every test case

153 test cases

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

Agents12

Structured Extraction62

Coding32

Grounded Answers40

Instruction Following52

Business Logic11

Security & permissions65

Diagnosis & investigation00

26 won by Flint14 won by Spark X2.6 4B113 tied