Claude Haiku 5.5 vs Flint, head to head

Side A

Side B

Overall

Claude Haiku 5.5 is clearly better. It wins 83 of the 84 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 3.2× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAClaude Haiku 5.5BFlintClaude Haiku 5.5Flint

Overall

7025.5s

3.9K10.9K

211m 17s

Agents

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

6139.5s

3.7K4.8K

1447.7s

Structured Extraction

Turns logs, diffs and records into exact JSON

9013.5s

2.6K10.9K

291m 17s

Coding

Writes code and SQL that pass hidden tests

8630.6s

6.8K12K

141m 19s

Grounded Answers

Answers from the given documents with sources, never guesses

7613.9s

2.2K8.7K

2957.7s

Instruction Following

Applies every rule, including ones changed mid-conversation

9431.5s

4.3K22.2K

352m 28s

Business Logic

Computes billing, scheduling and pricing rules exactly

6726.0s

5.5K11.7K

101m 20s

Security & permissions

Ignores planted instructions, still does the allowed work

6723.4s

2.7K7.1K

3552.6s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

1725.5s

2.3K7.3K

057.0s

What you'd run

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

SpecAClaude Haiku 5.5BFlint

Speed

225 tok/s

149 tok/s

Machine

Hosted

Memory at 32K

—

Context

256K

Cost per run

$0.42

Not measured

Cost per case

$0.0028

Not measured

Time per case

25.5s

1m 17s

Quantization

—

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.

Claude Haiku 5.5Flint

Every test case

153 test cases

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

Agents110

Structured Extraction130

Coding150

Grounded Answers100

Instruction Following130

Business Logic120

Security & permissions81

Diagnosis & investigation10

83 won by Claude Haiku 5.51 won by Flint69 tied