Introducing Parallel Decisions API: the first decision engine with world knowledge built in. Learn more.[Learn more.]
Search Capability Leaderboard

Mistral Large 4.0

Mistral AIClosed

Evaluated

#32 in Search Intelligence

Search Intelligence Score

64.4

+43.0 lift from search

050100
Lift from search
+43.0
21.4 without search
Cost per 1K tasks
$136
Below the median score of 66.0, so not ranked on cost

Accuracy by benchmark

Accuracy on each eval, with search (solid) and without (light).

  • DSQA82.3 vs 26.2
  • HLE41.0 vs 31.0
  • WISER70.0 vs 7.0

Cost per 1K tasks

How the cost splits between model inference, search calls, and page extraction.

Inference
$116
85%
Search
$7.68
6%
Extract
$13.1
10%

Compared with

Other models from the same provider alongside models that score closest.

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.

# Mistral Large 4.0 / Search Capability Leaderboard

  • Search Intelligence Score: 64.4 (#32 in Search Intelligence)
  • Without search: 21.4 / Lift from search +43.0
  • Cost per 1K tasks: $136 (below the median score of 66.0, so not ranked on cost)
  • Evaluated:
  • Lab: Mistral AI / Weights: Closed / Model id: mistral/mistral-large-4.0

## Accuracy by benchmark

SuiteWith searchWithout search
DSQA82.326.2
HLE41.031.0
WISER70.07.0

## Compared with

ModelScoreLiftCost per 1K tasks
Mistral Large 4.064.4+43.0$136
MiMo v2.6 Pro64.4+34.7$76.5
Hy4 Preview64.6+33.9$93.2
Kimi K364.2+33.6$266
Gemini 3.8 Flash65.1+26.1$177

Leaderboard last updated . Methodology: /leaderboard#methodology