Noometry

Model comparison

Pixtral Large vs Yi-1.5-34B

Pixtral Large is the stronger model overall, scoring 32.2 to 30.6 on the Noometry Index.

Last verified . 0 shared benchmarks.

Pixtral Large Mistral AI

32.2

Rank #259 Reported

Yi-1.5-34B 01.AI

30.6

Rank #289 Confirmed

Summary

  • The widest gap is in writing & preference, where Yi-1.5-34B leads 37.4 to 32.9.

Side by side

Pixtral LargeYi-1.5-34B
ProviderMistral AI01.AI
Noometry Index32.230.6
Released2024-11-012024-05-13
WeightsOpenOpen
Context window128K—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked321

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

Category by category

Coding Not comparable

Pixtral Large: —, Yi-1.5-34B: 32.4 (#272)

BenchmarkPixtral LargeYi-1.5-34B
BigCodeBench Instruct—33.9%
LMArena Coding—1169
BigCodeBench Complete—43.8%

Reasoning Too close to call

Pixtral Large: 21.7 (#218), Yi-1.5-34B: 22.5 (#191)

BenchmarkPixtral LargeYi-1.5-34B
EnigmaEval0.8%—
LMArena Hard Prompts—1160

Math Not comparable

Pixtral Large: —, Yi-1.5-34B: 27.5 (#249)

BenchmarkPixtral LargeYi-1.5-34B
LMArena Math—1182
MATH Level 5—25.5%

Knowledge Not comparable

Pixtral Large: —, Yi-1.5-34B: 14.8 (#295)

BenchmarkPixtral LargeYi-1.5-34B
GPQA Diamond—32%
LMArena Expert—1144

Multimodal Not comparable

Pixtral Large: 30.6 (#111), Yi-1.5-34B: —

BenchmarkPixtral LargeYi-1.5-34B
LMArena Vision1089—

Multilingual Not comparable

Pixtral Large: —, Yi-1.5-34B: 32.3 (#256)

BenchmarkPixtral LargeYi-1.5-34B
LMArena Non-English—1121
LMArena Chinese—1213
LMArena French—1156
LMArena German—1111
LMArena Japanese—1021
LMArena Korean—1005
LMArena Russian—1091
LMArena Spanish—1121

Instruction Following Not comparable

Pixtral Large: —, Yi-1.5-34B: 59.2 (#257)

BenchmarkPixtral LargeYi-1.5-34B
LMArena Instruction Following—1139

Long Context Not comparable

Pixtral Large: —, Yi-1.5-34B: 34.6 (#248)

BenchmarkPixtral LargeYi-1.5-34B
LMArena Longer Query—1143

Writing & Preference Yi-1.5-34B leads

Pixtral Large: 32.9 (#278), Yi-1.5-34B: 37.4 (#257)

BenchmarkPixtral LargeYi-1.5-34B
LMArena Text—1173
LMArena Creative Writing—1135
EQ-Bench Creative Writing988—
LMArena Multi-Turn—1153

Frequently asked questions

Is Pixtral Large better than Yi-1.5-34B?

Pixtral Large is the stronger model overall, scoring 32.2 to 30.6 on the Noometry Index.

How many benchmarks do Pixtral Large and Yi-1.5-34B share?

0 benchmarks have published results for both models. Pixtral Large has 3 scored results on Noometry and Yi-1.5-34B has 21.

Related comparisons

Go deeper