Model comparison

Qwen1.5-32B vs Yi 6B

Qwen1.5-32B has enough public results to be ranked (#293); Yi 6B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Yi 6B 01.AI

—

Unranked

Summary

  • They share 1 benchmark with published results for both.

Side by side

Qwen1.5-32B and Yi 6B specifications
Qwen1.5-32BYi 6B
ProviderAlibaba (Qwen)01.AI
Noometry Index30.5—
Released2024-02-042023-11-02
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked217

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

Category by category

Coding Not comparable

Qwen1.5-32B: 31.7 (#282), Yi 6B: —

Coding benchmarks
BenchmarkQwen1.5-32BYi 6B
BigCodeBench Instruct32.3%—
LMArena Coding1155—
BigCodeBench Complete42%—

Reasoning Not comparable

Qwen1.5-32B: 21.8 (#212), Yi 6B: —

Reasoning benchmarks
BenchmarkQwen1.5-32BYi 6B
LMArena Hard Prompts1130—
BIG-Bench Hard—47.2%
Epoch Capabilities Index—104.77
HellaSwag—74.4%
WinoGrande—71.3%

Math Not comparable

Qwen1.5-32B: 33.0 (#207), Yi 6B: —

Math benchmarks
BenchmarkQwen1.5-32BYi 6B
LMArena Math1155—
GSM8K—44.9%

Knowledge Not comparable

Qwen1.5-32B: 13.5 (#296), Yi 6B: —

Knowledge benchmarks
BenchmarkQwen1.5-32BYi 6B
MMLU74.4%64%
GPQA Diamond30.7%—
LMArena Expert1126—
ARC (AI2) Challenge—50.3%

Multilingual Not comparable

Qwen1.5-32B: 31.4 (#259), Yi 6B: —

Multilingual benchmarks
BenchmarkQwen1.5-32BYi 6B
LMArena Non-English1106—
LMArena Chinese1177—
LMArena French1101—
LMArena German1058—
LMArena Japanese1027—
LMArena Korean1008—
LMArena Russian1073—
LMArena Spanish1089—

Instruction Following Not comparable

Qwen1.5-32B: 57.7 (#265), Yi 6B: —

Instruction Following benchmarks
BenchmarkQwen1.5-32BYi 6B
LMArena Instruction Following1116—

Long Context Not comparable

Qwen1.5-32B: 34.7 (#246), Yi 6B: —

Long Context benchmarks
BenchmarkQwen1.5-32BYi 6B
LMArena Longer Query1146—

Writing & Preference Not comparable

Qwen1.5-32B: 34.2 (#271), Yi 6B: —

Writing & Preference benchmarks
BenchmarkQwen1.5-32BYi 6B
LMArena Text1137—
LMArena Creative Writing1083—
LMArena Multi-Turn1140—

Frequently asked questions

Is Qwen1.5-32B better than Yi 6B?

Qwen1.5-32B has enough public results to be ranked (#293); Yi 6B does not yet, so treat this comparison as directional.

How many benchmarks do Qwen1.5-32B and Yi 6B share?

1 benchmark has published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Yi 6B has 7.

Related comparisons

Go deeper