Model comparison

Olmo 2 0325 32b Instruct vs Yi 6B

Olmo 2 0325 32b Instruct has enough public results to be ranked (#248); Yi 6B does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Side by side

Olmo 2 0325 32b Instruct and Yi 6B specifications
Olmo 2 0325 32b InstructYi 6B
ProviderAllen Institute for AI (Ai2)01.AI
Noometry Index32.2—
Released—2023-11-02
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked167

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

Category by category

Coding Not comparable

Olmo 2 0325 32b Instruct: 34.6 (#222), Yi 6B: —

Coding benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
LMArena Coding1210—

Reasoning Not comparable

Olmo 2 0325 32b Instruct: 22.6 (#174), Yi 6B: —

Reasoning benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
LMArena Hard Prompts1208—
BIG-Bench Hard—47.2%
Epoch Capabilities Index—104.37
HellaSwag—74.4%
WinoGrande—71.3%

Math Not comparable

Olmo 2 0325 32b Instruct: 24.8 (#255), Yi 6B: —

Math benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
Omni-MATH16.1%—
LMArena Math1208—
GSM8K—44.9%

Knowledge Not comparable

Olmo 2 0325 32b Instruct: 19.2 (#274), Yi 6B: —

Knowledge benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
MMLU-Pro41.4%—
GPQA (HELM)28.7%—
ARC (AI2) Challenge—50.3%
MMLU—64%

Multilingual Not comparable

Olmo 2 0325 32b Instruct: 35.0 (#243), Yi 6B: —

Multilingual benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
LMArena Non-English1160—
LMArena Chinese1192—
LMArena Russian1187—

Instruction Following Not comparable

Olmo 2 0325 32b Instruct: 61.8 (#238), Yi 6B: —

Instruction Following benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
IFEval78%—
LMArena Instruction Following1186—

Long Context Not comparable

Olmo 2 0325 32b Instruct: 36.2 (#229), Yi 6B: —

Long Context benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
LMArena Longer Query1194—

Writing & Preference Not comparable

Olmo 2 0325 32b Instruct: 42.3 (#231), Yi 6B: —

Writing & Preference benchmarks
BenchmarkOlmo 2 0325 32b InstructYi 6B
LMArena Text1218—
LMArena Creative Writing1199—
WildBench73.4%—
LMArena Multi-Turn1221—

Frequently asked questions

Is Olmo 2 0325 32b Instruct better than Yi 6B?

Olmo 2 0325 32b Instruct has enough public results to be ranked (#248); Yi 6B does not yet, so treat this comparison as directional.

How many benchmarks do Olmo 2 0325 32b Instruct and Yi 6B share?

0 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Yi 6B has 7.

Related comparisons

Go deeper