Search Capability Leaderboard
MiniMax M3.1 Flash
MiniMaxClosed
Evaluated
1Gold · Search Efficiency
#11 in Search Intelligence
Search Intelligence Score
68.8
+41.7 lift from search
050100
- Lift from search
- +41.7
- 27.1 without search
- Cost per 1K tasks
- $43.8
- #1 in Search Efficiency
Accuracy by benchmark
Accuracy on each eval, with search (solid) and without (light).
- DSQA85.4 vs 31.3
- HLE50.0 vs 46.0
- WISER71.0 vs 4.0
Cost per 1K tasks
How the cost splits between model inference, search calls, and page extraction.
- Inference
- $23.7
- 54%
- Search
- $4.75
- 11%
- Extract
- $15.3
- 35%
Compared with
Other models from the same provider alongside models that score closest.
- MiniMax M3.1 Flash68.8Cost $43.8 · Lift +41.7
- MiniMax M352.6Cost $41.1 · Lift +29.5
- DS Flash 4.1 101768.9Cost $125 · Lift +36.0
- Pareto 26.1068.6Cost $116 · Lift +33.8
- Ember-167.9Cost $335 · Lift +38.0
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| MiniMax M3.1 Flash | 68.8 | +41.7 | $43.8 |
| MiniMax M3MiniMax M3 | 52.6 | +29.5 | $41.1 |
| DS Flash 4.1 1017DeepSeek V4.1 Flash (1017) | 68.9 | +36.0 | $125 |
| Pareto 26.10Pareto 26.10 | 68.6 | +33.8 | $116 |
| Ember-1Ember-1 | 67.9 | +38.0 | $335 |
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 M3.1 Flash · Search Capability Leaderboard
- Search Intelligence Score: 68.8 (#11 in Search Intelligence)
- Without search: 27.1 · Lift from search +41.7
- Cost per 1K tasks: $43.8 (#1 in Search Efficiency)
- Medals: Gold, Search Efficiency
- Evaluated:
- Lab: MiniMax · Weights: Closed · Model id: minimax/minimax-m3.1-flash
## Accuracy by benchmark
| Suite | With search | Without search |
|---|---|---|
| DSQA | 85.4 | 31.3 |
| HLE | 50.0 | 46.0 |
| WISER | 71.0 | 4.0 |
## Compared with
| Model | Score | Lift | Cost per 1K tasks |
|---|---|---|---|
| MiniMax M3.1 Flash | 68.8 | +41.7 | $43.8 |
| MiniMax M3 | 52.6 | +29.5 | $41.1 |
| DeepSeek V4.1 Flash (1017) | 68.9 | +36.0 | $125 |
| Pareto 26.10 | 68.6 | +33.8 | $116 |
| Ember-1 | 67.9 | +38.0 | $335 |
Leaderboard last updated . Methodology: /leaderboard#methodology