MiMo-V2.6-Pro vs Mistral Large 4
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. MiMo-V2.6-Pro spends 1.2× as many thinking tokens per test case.
TaskAMiMo-V2.6-ProBMistral Large 4
Overall
482m 13s
281m 56s
Agents
474m 48s
1126.1s
Structured Extraction
601m 26s
153.78s
Coding
242m 58s
332m 48s
Grounded Answers
621m 9s
382m 45s
Instruction Following
591m 23s
693m 47s
Business Logic
571m 52s
242m 40s
Security & permissions
711m 41s
331m 9s
Diagnosis & investigation
02m 54s
01m 19s
What you'd run
The build behind each score. Orange marks the faster, smaller, cheaper or longer-context side.
SpecAMiMo-V2.6-ProBMistral Large 4
Speed
55 tok/s
56 tok/s (better)
Machine
Hosted
Hosted
Memory at 32K
—
—
Context
1.1M (better)
512K
Cost per run
$1.80 (better)
$2.67
Cost per case
$0.012 (better)
$0.017
Time per case
2m 13s
1m 56s (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