[mle]/DaBench

Claude Haiku 5.5 vs Ling 3.1 Flash

Side A
Model page
Side B
Model page
Overall
70
vs
Overall
45

Claude Haiku 5.5 is clearly better. It wins 50 of the 56 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. Ling 3.1 Flash spends 1.9× as many thinking tokens per test case.

Thinking tokensAnswer tokens
TaskAB
Overall
7025.5s
3.9K, 78% thinking7.9K, 73% thinking
451m 16s
Agents
6139.5s
3.7K, 61% thinking4.5K, 66% thinking
4155.9s
Structured Extraction
9013.5s
2.6K, 83% thinking8.1K, 69% thinking
711m 11s
Coding
8630.6s
6.8K, 76% thinking11.3K, 89% thinking
241m 42s
Grounded Answers
7613.9s
2.2K, 78% thinking6.7K, 74% thinking
5258.9s
Instruction Following
9431.5s
4.3K, 82% thinking11.4K, 77% thinking
761m 55s
Business Logic
6726.0s
5.5K, 95% thinking9.7K, 56% thinking
381m 22s
Security & permissions
6723.4s
2.7K, 70% thinking5.2K, 74% thinking
5456.1s
Diagnosis & investigation
1725.5s
2.3K, 50% thinking3.2K, 72% thinking
042.1s

What you'd run

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

SpecAB
Speed
225 tok/s (better)
112 tok/s
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
1M (better)
256K
Cost per run
$0.42
Not measured
Cost per case
$0.0028
Not measured
Time per case
25.5s (better)
1m 16s
Quantization
—
—
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.

Claude Haiku 5.5Ling 3.1 Flash
025507510050100150Perfect run7045

Every test case

153 test cases

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

50 won by Claude Haiku 5.56 won by Ling 3.1 Flash97 tied