[mle]/DaBench

Apodex 1.1 Mini (free) vs Mistral Large 4

Side A
Model page
Side B
Model page
Overall
25
vs
Overall
28

Too close to call. Mistral Large 4 wins 29 of the 50 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 1.4× as many thinking tokens per test case.

Thinking tokensAnswer tokens
TaskAB
Overall
2535.1s
8.5K, 75% thinking6.2K, 72% thinking
281m 56s
Agents
2639.4s
6.2K, 69% thinking795, no thinking
1126.1s
Structured Extraction
5227.2s
7.7K, 68% thinking288, no thinking
153.78s
Coding
446.5s
12.1K, 94% thinking9.3K, 37% thinking
332m 48s
Grounded Answers
2926.0s
6.9K, 70% thinking8.1K, 89% thinking
382m 45s
Instruction Following
3644.5s
11.4K, 79% thinking12.9K, 84% thinking
693m 47s
Business Logic
1435.4s
10K, 56% thinking8.8K, 77% thinking
242m 40s
Security & permissions
4027.3s
5.8K, 76% thinking3.7K, 83% thinking
331m 9s
Diagnosis & investigation
034.6s
5.1K, 84% thinking4.4K, 85% thinking
01m 19s

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)
56 tok/s
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
256K
512K (better)
Cost per run
Not measured
$2.67
Cost per case
Not measured
$0.017
Time per case
35.1s (better)
1m 56s
Quantization
BF16
—
Harness
openrouter
openrouter

The race

3 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)Mistral Large 4
025507510050100150Perfect run2528

Every test case

153 test cases

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

21 won by Apodex 1.1 Mini (free)29 won by Mistral Large 4103 tied