Noometry

Model comparison

Mistral Nemo vs Qwen1.5-72B

Qwen1.5-72B is the stronger model overall, scoring 30.3 to 25.9 on the Noometry Index.

Last verified . 1 shared benchmarks.

Mistral Nemo Mistral AI

25.9

Rank #332 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 1 benchmark with published results for both. Mistral Nemo scores higher in 1 category and Qwen1.5-72B in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen1.5-72B leads 37.4 to 28.6.

Side by side

Mistral NemoQwen1.5-72B
ProviderMistral AIAlibaba (Qwen)
Noometry Index25.930.3
Released2024-07-012024-02-04
WeightsOpenOpen
Context window128K—
Max output128K—
Input $ / M tokens$0.15—
Output $ / M tokens$0.15—
Results tracked1022

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

Category by category

Coding Not comparable

Mistral Nemo: —, Qwen1.5-72B: 31.4 (#272)

BenchmarkMistral NemoQwen1.5-72B
BigCodeBench Instruct—33.2%
LMArena Coding—1166
BigCodeBench Complete—40.3%
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Mistral Nemo: 23.3 (#118), Qwen1.5-72B: —

BenchmarkMistral NemoQwen1.5-72B
Berkeley Function Calling Leaderboard27.6%—
BALROG17.6%—

Reasoning Qwen1.5-72B leads

Mistral Nemo: 19.9 (#230), Qwen1.5-72B: 21.2 (#201)

BenchmarkMistral NemoQwen1.5-72B
LMArena Hard Prompts—1148
DTBench48.6%—
Epoch Capabilities Index118.63—
PIQA83.5%—

Math Qwen1.5-72B leads

Mistral Nemo: 23.5 (#263), Qwen1.5-72B: 30.7 (#205)

BenchmarkMistral NemoQwen1.5-72B
LMArena Math—1164
MATH Level 510.8%—
GSM8K84.2%—

Knowledge Too close to call

Mistral Nemo: 12.3 (#293), Qwen1.5-72B: 11.5 (#295)

BenchmarkMistral NemoQwen1.5-72B
GPQA Diamond29.9%28.8%
LMArena Expert—1136
BoolQ82.5%—

Multilingual Not comparable

Mistral Nemo: —, Qwen1.5-72B: 33.4 (#248)

BenchmarkMistral NemoQwen1.5-72B
LMArena Non-English—1135
LMArena Chinese—1186
LMArena French—1158
LMArena German—1084
LMArena Japanese—1061
LMArena Korean—1049
LMArena Russian—1104
LMArena Spanish—1110

Instruction Following Not comparable

Mistral Nemo: —, Qwen1.5-72B: 59.6 (#251)

BenchmarkMistral NemoQwen1.5-72B
LMArena Instruction Following—1142

Long Context Not comparable

Mistral Nemo: —, Qwen1.5-72B: 35.0 (#238)

BenchmarkMistral NemoQwen1.5-72B
LMArena Longer Query—1157

Writing & Preference Qwen1.5-72B leads

Mistral Nemo: 28.6 (#291), Qwen1.5-72B: 37.4 (#253)

BenchmarkMistral NemoQwen1.5-72B
LMArena Text—1166
LMArena Creative Writing—1137
EQ-Bench Creative Writing881—
LMArena Multi-Turn—1160

Frequently asked questions

Is Mistral Nemo better than Qwen1.5-72B?

Qwen1.5-72B is the stronger model overall, scoring 30.3 to 25.9 on the Noometry Index.

How many benchmarks do Mistral Nemo and Qwen1.5-72B share?

1 benchmark has published results for both models. Mistral Nemo has 10 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper