Noometry

Model comparison

Mistral Nemo vs Qwen1.5-14B

Qwen1.5-14B is the stronger model overall, scoring 32.7 to 26.4 on the Noometry Index.

Last verified . 0 shared benchmarks.

Mistral Nemo Mistral AI

26.4

Rank #337 Confirmed

Qwen1.5-14B Alibaba (Qwen)

32.7

Rank #253 Confirmed

Summary

  • The widest gap is in knowledge, where Qwen1.5-14B leads 29.8 to 12.3.

Side by side

Mistral NemoQwen1.5-14B
ProviderMistral AIAlibaba (Qwen)
Noometry Index26.432.7
Released2024-07-012024-02-04
WeightsOpenOpen
Context window128K—
Max output128K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.15—
Results tracked1017

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

Category by category

Coding Not comparable

Mistral Nemo: —, Qwen1.5-14B: 33.1 (#263)

BenchmarkMistral NemoQwen1.5-14B
LMArena Coding—1138

Agentic & Tool Use Not comparable

Mistral Nemo: 23.5 (#125), Qwen1.5-14B: —

BenchmarkMistral NemoQwen1.5-14B
Berkeley Function Calling Leaderboard27.6%—
BALROG17.6%—

Reasoning Too close to call

Mistral Nemo: 20.7 (#232), Qwen1.5-14B: 21.4 (#223)

BenchmarkMistral NemoQwen1.5-14B
LMArena Hard Prompts—1113
DTBench48.6%—
Epoch Capabilities Index118.68—
PIQA83.5%—

Math Qwen1.5-14B leads

Mistral Nemo: 25.5 (#268), Qwen1.5-14B: 32.4 (#215)

BenchmarkMistral NemoQwen1.5-14B
LMArena Math—1125
MATH Level 510.8%—
GSM8K84.2%—

Knowledge Qwen1.5-14B leads

Mistral Nemo: 12.3 (#298), Qwen1.5-14B: 29.8 (#232)

BenchmarkMistral NemoQwen1.5-14B
GPQA Diamond29.9%—
LMArena Expert—1094
BoolQ82.5%—
MMLU—68.6%

Multilingual Not comparable

Mistral Nemo: —, Qwen1.5-14B: 30.7 (#262)

BenchmarkMistral NemoQwen1.5-14B
LMArena Non-English—1095
LMArena Chinese—1147
LMArena French—1116
LMArena German—1043
LMArena Japanese—1019
LMArena Russian—1046
LMArena Spanish—1085

Instruction Following Not comparable

Mistral Nemo: —, Qwen1.5-14B: 56.8 (#271)

BenchmarkMistral NemoQwen1.5-14B
LMArena Instruction Following—1102

Long Context Not comparable

Mistral Nemo: —, Qwen1.5-14B: 33.7 (#257)

BenchmarkMistral NemoQwen1.5-14B
LMArena Longer Query—1113

Writing & Preference Qwen1.5-14B leads

Mistral Nemo: 28.5 (#296), Qwen1.5-14B: 33.6 (#276)

BenchmarkMistral NemoQwen1.5-14B
LMArena Text—1128
LMArena Creative Writing—1091
EQ-Bench Creative Writing881—
LMArena Multi-Turn—1110

Frequently asked questions

Is Mistral Nemo better than Qwen1.5-14B?

Qwen1.5-14B is the stronger model overall, scoring 32.7 to 26.4 on the Noometry Index.

How many benchmarks do Mistral Nemo and Qwen1.5-14B share?

0 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen1.5-14B has 17.

Related comparisons

Go deeper