Model comparison

Falcon-7B vs Mistral Medium 3.1

Mistral Medium 3.1 has enough public results to be ranked (#266); Falcon-7B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Summary

  • Falcon-7B has downloadable open weights; the other is API-only.

Side by side

Falcon-7B and Mistral Medium 3.1 specifications
Falcon-7BMistral Medium 3.1
ProviderTechnology Innovation InstituteMistral AI
Noometry Index—31.9
Released2023-04-24—
WeightsOpenProprietary
Context window—131K
Max output—105K
Input $ / M tokens—$0.40
Output $ / M tokens—$2
Results tracked123

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Reasoning Not comparable

Falcon-7B: —, Mistral Medium 3.1: 10.6 (#341)

Reasoning benchmarks
BenchmarkFalcon-7BMistral Medium 3.1
NYT Connections (extended)—6.5%
Thematic Generalization—20.3%
BIG-Bench Hard28.8%—
Epoch Capabilities Index95.1—
HellaSwag78.1%—
LAMBADA74.9%—
PIQA80.3%—
WinoGrande67.2%—

Math Not comparable

Falcon-7B: —, Mistral Medium 3.1: —

Math benchmarks
BenchmarkFalcon-7BMistral Medium 3.1
GSM8K6.8%—

Knowledge Not comparable

Falcon-7B: —, Mistral Medium 3.1: —

Knowledge benchmarks
BenchmarkFalcon-7BMistral Medium 3.1
ARC (AI2) Challenge47.9%—
BoolQ75.3%—
MMLU35%—
OpenBookQA51.6%—
TriviaQA64.6%—

Writing & Preference Not comparable

Falcon-7B: —, Mistral Medium 3.1: 55.5 (#145)

Writing & Preference benchmarks
BenchmarkFalcon-7BMistral Medium 3.1
EQ-Bench Creative Writing—1476

Frequently asked questions

Is Falcon-7B better than Mistral Medium 3.1?

Mistral Medium 3.1 has enough public results to be ranked (#266); Falcon-7B does not yet, so treat this comparison as directional.

How many benchmarks do Falcon-7B and Mistral Medium 3.1 share?

0 benchmarks have published results for both models. Falcon-7B has 12 scored results on Noometry and Mistral Medium 3.1 has 3.

Related comparisons

Go deeper