Search Intelligence Score
49.5
+36.1 lift from search
050100
- Lift from search
- +36.1
- 13.4 without search
- Cost per 1K tasks
- $23.5
- Below the median score of 64.4, so not ranked on cost
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA63.5 vs 25.2
- HLE29.0 vs 12.0
- WISER56.0 vs 3.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $9.83
- 42%
- Search
- $7.57
- 32%
- Extract
- $6.15
- 26%
Compared with
Other models from the same provider alongside models that score closest.
- MiMo v2.549.5Cost $23.5 · Lift +36.1
- MiMo v2.6 Flash60.9Cost $25.2 · Lift +38.5
- MiMo v2.6 Pro64.4Cost $76.5 · Lift +34.7
- MiniMax M352.6Cost $41.1 · Lift +29.5
- Nem 3 Ultra53.0Cost $113 · Lift +37.7
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| MiMo v2.5 | 49.5 | +36.1 | $23.5 |
| MiMo v2.6 FlashMiMo v2.6 Flash | 60.9 | +38.5 | $25.2 |
| MiMo v2.6 ProMiMo v2.6 Pro | 64.4 | +34.7 | $76.5 |
| MiniMax M3MiniMax M3 | 52.6 | +29.5 | $41.1 |
| Nem 3 UltraNemotron 3 Ultra 550B | 53.0 | +37.7 | $113 |
Search Intelligence Score averages accuracy on DSQA, HLE, and WISER with equal weight; cost is averaged the same way, with cost shown per 1,000 tasks. Evaluated . Leaderboard last updated . Full methodology.
# MiMo v2.5 · Search Capability Leaderboard
- Search Intelligence Score: 49.5 (#46 in Search Intelligence)
- Without search: 13.4 · Lift from search +36.1
- Cost per 1K tasks: $23.5 (below the median score of 64.4, so not ranked on cost)
- Evaluated:
- Lab: Xiaomi · Weights: Open weights · Model id: xiaomi/mimo-v2.5
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 63.5 | 25.2 |
| HLE | 29.0 | 12.0 |
| WISER | 56.0 | 3.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| MiMo v2.5 | 49.5 | +36.1 | $23.5 |
| MiMo v2.6 Flash | 60.9 | +38.5 | $25.2 |
| MiMo v2.6 Pro | 64.4 | +34.7 | $76.5 |
| MiniMax M3 | 52.6 | +29.5 | $41.1 |
| Nemotron 3 Ultra 550B | 53.0 | +37.7 | $113 |
Leaderboard last updated . Methodology: /leaderboard#methodology