Flint vs GPT-6 Luna, head to head

Side A

Side B

Overall

GPT-6 Luna is clearly better. It wins 70 of the 71 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 7.2× as many thinking tokens per test case.

Thinking tokensAnswer tokens

TaskAFlintBGPT-6 LunaFlintGPT-6 Luna

Overall

211m 17s

10.9K1.9K

6149.1s

Agents

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

1447.7s

4.8K1.3K

561m 18s

Structured Extraction

Turns logs, diffs and records into exact JSON

291m 17s

10.9K999

9514.5s

Coding

Writes code and SQL that pass hidden tests

141m 19s

12K3.6K

732m 18s

Grounded Answers

Answers from the given documents with sources, never guesses

2957.7s

8.7K1.1K

6715.6s

Instruction Following

Applies every rule, including ones changed mid-conversation

352m 28s

22.2K2K

8432.3s

Business Logic

Computes billing, scheduling and pricing rules exactly

101m 20s

11.7K3.2K

3743.1s

Security & permissions

Ignores planted instructions, still does the allowed work

3552.6s

7.1K1K

6224.5s

Diagnosis & investigation

Chooses diagnostic checks, repairs supported causes and verifies recovery

057.0s

7.3K1.1K

1737.7s

What you'd run

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

SpecAFlintBGPT-6 Luna

Speed

149 tok/s

90 tok/s

Machine

Hosted

Memory at 32K

—

Context

256K

1.1M

Cost per run

Not measured

$0.10

Cost per case

Not measured

$0.00067

Time per case

1m 17s

49.1s

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.

FlintGPT-6 Luna

Every test case

153 test cases

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

Agents110

Structured Extraction014

Coding014

Grounded Answers08

Instruction Following011

Business Logic06

Security & permissions06

Diagnosis & investigation01

1 won by Flint70 won by GPT-6 Luna82 tied