Flint vs Ling 3.1 Flash
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 1.7× as many thinking tokens per test case.
TaskAFlintBLing 3.1 Flash
Overall
211m 17s
451m 16s
Agents
1447.7s
4155.9s
Structured Extraction
291m 17s
711m 11s
Coding
141m 19s
241m 42s
Grounded Answers
2957.7s
5258.9s
Instruction Following
352m 28s
761m 55s
Business Logic
101m 20s
381m 22s
Security & permissions
3552.6s
5456.1s
Diagnosis & investigation
057.0s
042.1s
What you'd run
The build behind each score. Orange marks the faster, smaller, cheaper or longer-context side.
SpecAFlintBLing 3.1 Flash
Speed
149 tok/s (better)
112 tok/s
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
256K
256K
Cost per run
Not measured
Not measured
Cost per case
Not measured
Not measured
Time per case
1m 17s
1m 16s (better)
Quantization
BF16
—
Harness
openrouter
openrouter
The race
Each model's running score as the test cases go by. The dashed line is a perfect run.
Every test case
Each square is one test case, colored by the model that scored higher.
Agents
Structured Extraction
Coding
Grounded Answers
Instruction Following
Business Logic
Security & permissions
Diagnosis & investigation