[mle]/DaBench

Ling 3.1 Flash vs Muse Spark 1.3 Contributor

Side A
Model page
Side B
Model page
Overall
45
vs
Overall
66

Muse Spark 1.3 Contributor is clearly better. It wins 44 of the 51 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. Muse Spark 1.3 Contributor spends 1.4× as many thinking tokens per test case.

Thinking tokensAnswer tokens
TaskAB
Overall
451m 16s
7.9K, 73% thinking8.7K, 91% thinking
661m 42s
Agents
4155.9s
4.5K, 66% thinking14.7K, 88% thinking
573m 16s
Structured Extraction
711m 11s
8.1K, 69% thinking4.2K, 91% thinking
9037.9s
Coding
241m 42s
11.3K, 89% thinking10.8K, 95% thinking
482m 1s
Grounded Answers
5258.9s
6.7K, 74% thinking6.1K, 91% thinking
811m 1s
Instruction Following
761m 55s
11.4K, 77% thinking8.7K, 91% thinking
841m 18s
Business Logic
381m 22s
9.7K, 56% thinking6K, 95% thinking
761m 7s
Security & permissions
5456.1s
5.2K, 74% thinking8.2K, 87% thinking
761m 59s
Diagnosis & investigation
042.1s
3.2K, 72% thinking17.2K, 90% thinking
173m 34s

What you'd run

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

SpecAB
Speed
112 tok/s (better)
107 tok/s
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
256K
1M (better)
Cost per run
Not measured
$0.41
Cost per case
Not measured
$0.0027
Time per case
1m 16s (better)
1m 42s
Quantization
—
—
Harness
openrouter
openrouter

The race

2 lead changes

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

Ling 3.1 FlashMuse Spark 1.3 Contributor
025507510050100150Perfect run4566

Every test case

153 test cases

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

7 won by Ling 3.1 Flash44 won by Muse Spark 1.3 Contributor102 tied