#75 MiMo-V2.5-Pro
none- Cost
- $0.004
- Time
- 46.4s
- Tokens
- 4,025 tok
Xiaomi
Release: 2026-04-22
Tested on: 2026-04-22 21:39
xiaomi/mimo-v2.5-pro::none
1.02T total (42B active)MoEOpen source
(medium)
(none)
Summary
MiMo-V2.5-Pro scores 5.8 on AI BENCHY and ranks #75. It has N/A reliability, a 46.3% pass rate, $0.033 total cost, and 1.51s average response time.
What makes MiMo-V2.5-Pro unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-08-12
- Parameters
- 1.02T total (42B active)
- Architecture
- MoE
- Availability
- Open source
- License
- MIT
5.8
Consistency
8.3
N/A
$0.033
Total Output Tokens
2,451
Total Input Tokens
0
Input Price
$1.000 / 1M
Output Price
$3.000 / 1M
Flaky tests
4
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:26 Re-test | 5.4 | 10.0 | $0.068 ↓ | Compare | |
| 2026-07-16 22:42 New test added | 5.5 | 10.0 | $0.068 ↓ | Compare | |
| 2026-06-04 13:48 New test added | 5.5 | 10.0 | $0.017 ↓ | Compare | |
| 2026-05-08 15:29 Suite changed | 5.7 | 10.0 | $0.035 | Compare | |
| 2026-04-22 21:39 First recorded run | 5.8 | N/A | $0.033 | Current run |
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-04-22 21:39 · First recorded run | 54/54 attempts | 5.8 | 8.3 | N/A | 6/18 | 4 | 2,451 | 0 | $0.033 | 1.51s |
| 2026-08-14 02:26 · Re-test | 66/66 attempts | 5.4 | 8.6 | 10.0 | 5/22 | 4 | 15,362 | 124,808 | $0.068 | 4.24s |
| Difference | — | +0.4 | -0.3 | +1 | 0 | -12911 | -124808 | -$0.036 | -2728ms |
Benchmark coverage differs: 54/54 attempts (Target: 3 repeats per test) versus 66/66 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
MiMo-V2.5-PrononevsGPT-5.6 LunanoneMiMo-V2.5-PrononevsKimi K2.5noneMiMo-V2.5-PrononevsKAT-Coder-Air V2.5lowMiMo-V2.5-PrononevsDeepSeek V4 Flash 0731noneMiMo-V2.5-PrononevsLaguna S 2.1mediumFree AvailableMiMo-V2.5-PrononevsLaguna S 2.1highFree AvailableMiMo-V2.5-PrononevsDeepSeek V4 Flash 0423noneMiMo-V2.5-PrononevsInkling SmallnoneMiMo-V2.5-PrononevsQwen3.8 27BnoneMiMo-V2.5-PrononevsLaguna XS 2.1noneFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 2.9 | 7.9 | |
| Coding | 6.4 | 3.3 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 4.5 | 10.0 | |
| Instructions following | 6.4 | 10.0 | |
| Puzzle Solving | 6.7 | 4.7 | |
| Tool Calling | 10.0 | 10.0 |