Search Intelligence Score
52.6
+29.5 lift from search
050100
- Lift from search
- +29.5
- 23.1 without search
- Cost per 1K tasks
- $41.1
- 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).
- DSQA64.8 vs 26.2
- HLE41.0 vs 37.0
- WISER52.0 vs 6.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $28.2
- 69%
- Search
- $4.06
- 10%
- Extract
- $8.77
- 21%
Compared with
Other models from the same provider alongside models that score closest.
- MiniMax M352.6Cost $41.1 · Lift +29.5
- MiniMax M3.1 Flash68.8Cost $43.8 · Lift +41.7
- Nem 3 Ultra53.0Cost $113 · Lift +37.7
- GLM-5.254.3Cost $66.6 · Lift +35.9
- MiMo v2.549.5Cost $23.5 · Lift +36.1
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| MiniMax M3 | 52.6 | +29.5 | $41.1 |
| MiniMax M3.1 FlashMiniMax M3.1 Flash | 68.8 | +41.7 | $43.8 |
| Nem 3 UltraNemotron 3 Ultra 550B | 53.0 | +37.7 | $113 |
| GLM-5.2GLM-5.2 | 54.3 | +35.9 | $66.6 |
| MiMo v2.5MiMo v2.5 | 49.5 | +36.1 | $23.5 |
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.
# MiniMax M3 · Search Capability Leaderboard
- Search Intelligence Score: 52.6 (#45 in Search Intelligence)
- Without search: 23.1 · Lift from search +29.5
- Cost per 1K tasks: $41.1 (below the median score of 64.4, so not ranked on cost)
- Evaluated:
- Lab: MiniMax · Weights: Open weights · Model id: minimax/minimax-m3
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 64.8 | 26.2 |
| HLE | 41.0 | 37.0 |
| WISER | 52.0 | 6.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| MiniMax M3 | 52.6 | +29.5 | $41.1 |
| MiniMax M3.1 Flash | 68.8 | +41.7 | $43.8 |
| Nemotron 3 Ultra 550B | 53.0 | +37.7 | $113 |
| GLM-5.2 | 54.3 | +35.9 | $66.6 |
| MiMo v2.5 | 49.5 | +36.1 | $23.5 |
Leaderboard last updated . Methodology: /leaderboard#methodology