Model comparison

Falcon 2 11B vs Mistral

Mistral has enough public results to be ranked (#303); Falcon 2 11B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Summary

  • Falcon 2 11B has downloadable open weights; the other is API-only.

Side by side

Falcon 2 11B and Mistral specifications
Falcon 2 11BMistral
ProviderTechnology Innovation InstituteMistral AI
Noometry Index—29.9
Released2024-05-09—
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked522

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

Category by category

Coding Not comparable

Falcon 2 11B: —, Mistral: 33.8 (#250)

Coding benchmarks
BenchmarkFalcon 2 11BMistral
LMArena Coding—1162

Reasoning Not comparable

Falcon 2 11B: —, Mistral: 22.2 (#200)

Reasoning benchmarks
BenchmarkFalcon 2 11BMistral
LMArena Hard Prompts—1149
Epoch Capabilities Index109.56—
HellaSwag82.9%—
WinoGrande78.3%—

Math Not comparable

Falcon 2 11B: —, Mistral: 22.3 (#278)

Math benchmarks
BenchmarkFalcon 2 11BMistral
Omni-MATH—7.2%
LMArena Math—1180
GSM8K53.8%—

Knowledge Not comparable

Falcon 2 11B: —, Mistral: 16.6 (#288)

Knowledge benchmarks
BenchmarkFalcon 2 11BMistral
MMLU-Pro—27.7%
GPQA (HELM)—30.3%
LMArena Expert—1125
MMLU58.4%—

Multilingual Not comparable

Falcon 2 11B: —, Mistral: 32.8 (#254)

Multilingual benchmarks
BenchmarkFalcon 2 11BMistral
LMArena Non-English—1129
LMArena Chinese—1109
LMArena French—1180
LMArena German—1155
LMArena Japanese—1013
LMArena Korean—1032
LMArena Russian—1168
LMArena Spanish—1143

Instruction Following Not comparable

Falcon 2 11B: —, Mistral: 52.6 (#288)

Instruction Following benchmarks
BenchmarkFalcon 2 11BMistral
IFEval—56.8%
LMArena Instruction Following—1152

Long Context Not comparable

Falcon 2 11B: —, Mistral: 35.0 (#245)

Long Context benchmarks
BenchmarkFalcon 2 11BMistral
LMArena Longer Query—1153

Writing & Preference Not comparable

Falcon 2 11B: —, Mistral: 37.0 (#260)

Writing & Preference benchmarks
BenchmarkFalcon 2 11BMistral
LMArena Text—1165
LMArena Creative Writing—1158
WildBench—66%
LMArena Multi-Turn—1147

Frequently asked questions

Is Falcon 2 11B better than Mistral?

Mistral has enough public results to be ranked (#303); Falcon 2 11B does not yet, so treat this comparison as directional.

How many benchmarks do Falcon 2 11B and Mistral share?

0 benchmarks have published results for both models. Falcon 2 11B has 5 scored results on Noometry and Mistral has 22.

Related comparisons

Go deeper