Flint vs MiMo-V2.6-Pro
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 1.9× as many thinking tokens per test case.
TaskAFlintBMiMo-V2.6-Pro
Overall
211m 17s
482m 13s
Agents
1447.7s
474m 48s
Structured Extraction
291m 17s
601m 26s
Coding
141m 19s
242m 58s
Grounded Answers
2957.7s
621m 9s
Instruction Following
352m 28s
591m 23s
Business Logic
101m 20s
571m 52s
Security & permissions
3552.6s
711m 41s
Diagnosis & investigation
057.0s
02m 54s
What you'd run
The build behind each score. Orange marks the faster, smaller, cheaper or longer-context side.
SpecAFlintBMiMo-V2.6-Pro
Speed
149 tok/s (better)
55 tok/s
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
256K
1.1M (better)
Cost per run
Not measured
$1.80
Cost per case
Not measured
$0.012
Time per case
1m 17s (better)
2m 13s
Quantization
BF16
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