[mle]/DaBench

Apodex 1.1 Mini (free) vs GPT-6 Luna

Side A
Model page
Side B
Model page
Overall
25
vs
Overall
61

GPT-6 Luna is clearly better. It wins 69 of the 72 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. Apodex 1.1 Mini (free) spends 4.6× as many thinking tokens per test case.

Thinking tokensAnswer tokens
TaskAB
Overall
2535.1s
8.5K, 75% thinking1.9K, 73% thinking
6149.1s
Agents
2639.4s
6.2K, 69% thinking1.3K, 67% thinking
561m 18s
Structured Extraction
5227.2s
7.7K, 68% thinking999, 72% thinking
9514.5s
Coding
446.5s
12.1K, 94% thinking3.6K, 60% thinking
732m 18s
Grounded Answers
2926.0s
6.9K, 70% thinking1.1K, 72% thinking
6715.6s
Instruction Following
3644.5s
11.4K, 79% thinking2K, 74% thinking
8432.3s
Business Logic
1435.4s
10K, 56% thinking3.2K, 93% thinking
3743.1s
Security & permissions
4027.3s
5.8K, 76% thinking1K, 68% thinking
6224.5s
Diagnosis & investigation
034.6s
5.1K, 84% thinking1.1K, 68% thinking
1737.7s

What you'd run

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

SpecAB
Speed
278 tok/s (better)
90 tok/s
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
256K
1.1M (better)
Cost per run
Not measured
$0.10
Cost per case
Not measured
$0.00067
Time per case
35.1s (better)
49.1s
Quantization
BF16
—
Harness
openrouter
openrouter

The race

No lead changes

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

Apodex 1.1 Mini (free)GPT-6 Luna
025507510050100150Perfect run2561

Every test case

153 test cases

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

3 won by Apodex 1.1 Mini (free)69 won by GPT-6 Luna81 tied