Model comparison

Mixtral 8x7B vs OLMo 2 Furious 13B

OLMo 2 Furious 13B is the stronger model overall, scoring 29.7 to 27.1 on the Noometry Index.

Last verified . 5 shared benchmarks.

Mixtral 8x7B Mistral AI

27.1

Rank #334 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Mixtral 8x7B scores higher in 2 categories and OLMo 2 Furious 13B in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where OLMo 2 Furious 13B leads 60.9 to 51.0.
  • The biggest single-benchmark swing is IFEval: 57.5% for Mixtral 8x7B and 73% for OLMo 2 Furious 13B.

Side by side

Mixtral 8x7B and OLMo 2 Furious 13B specifications
Mixtral 8x7BOLMo 2 Furious 13B
ProviderMistral AIAllen Institute for AI (Ai2)
Noometry Index27.129.7
Released2023-12-112024-12-31
WeightsOpenOpen
Context window32K—
Max output32K—
Input $ / M tokens$0.70—
Output $ / M tokens$0.70—
Results tracked3812

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

Category by category

Coding Mixtral 8x7B leads

Mixtral 8x7B: 32.8 (#269), OLMo 2 Furious 13B: 28.6 (#313)

Coding benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
LiveBench Coding—10.4%
LMArena Coding1126—
HumanEval+39.6%—
MBPP+49.7%—

Reasoning Mixtral 8x7B leads

Mixtral 8x7B: 18.2 (#285), OLMo 2 Furious 13B: 15.5 (#314)

Reasoning benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
LiveBench Reasoning—16.3%
LMArena Hard Prompts1115—
DTBench49.6%—
LiveBench Data Analysis—20.6%
Adversarial NLI55.2%—
Epoch Capabilities Index118.47—
ForecastBench56.3—
HellaSwag86.7%—
LiveBench—22.1%
PIQA83.6%—
WinoGrande77.2%—

Math OLMo 2 Furious 13B leads

Mixtral 8x7B: 18.8 (#289), OLMo 2 Furious 13B: 23.1 (#273)

Math benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
Omni-MATH10.5%15.6%
LiveBench Math—13.6%
LMArena Math1147—
MATH Level 510%—
GSM8K74.4%—

Knowledge OLMo 2 Furious 13B leads

Mixtral 8x7B: 11.0 (#301), OLMo 2 Furious 13B: 18.3 (#283)

Knowledge benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
MMLU-Pro33.5%31%
GPQA (HELM)29.6%31.6%
GPQA Diamond30.6%—
LMArena Expert1088—
ARC (AI2) Challenge87.3%—
MMLU70.6%—
OpenBookQA85.8%—
TriviaQA82.2%—

Multilingual Not comparable

Mixtral 8x7B: 29.6 (#266), OLMo 2 Furious 13B: —

Multilingual benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
LMArena Non-English1077—
LMArena Chinese1055—
LMArena French1166—
LMArena German1114—
LMArena Japanese931—
LMArena Korean968—
LMArena Russian1090—
LMArena Spanish1111—

Instruction Following OLMo 2 Furious 13B leads

Mixtral 8x7B: 51.0 (#297), OLMo 2 Furious 13B: 60.9 (#248)

Instruction Following benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
IFEval57.5%73%
LiveBench Instruction Following—60.6%
LMArena Instruction Following1109—

Long Context Not comparable

Mixtral 8x7B: 33.4 (#260), OLMo 2 Furious 13B: —

Long Context benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
LMArena Longer Query1103—

Writing & Preference OLMo 2 Furious 13B leads

Mixtral 8x7B: 34.2 (#270), OLMo 2 Furious 13B: 42.9 (#230)

Writing & Preference benchmarks
BenchmarkMixtral 8x7BOLMo 2 Furious 13B
WildBench67.3%68.9%
LMArena Text1132—
LMArena Creative Writing1109—
LMArena Multi-Turn1115—
LiveBench Language—11.2%

Frequently asked questions

Is Mixtral 8x7B better than OLMo 2 Furious 13B?

OLMo 2 Furious 13B is the stronger model overall, scoring 29.7 to 27.1 on the Noometry Index.

Is Mixtral 8x7B or OLMo 2 Furious 13B better for coding?

Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 28.6 in the Noometry coding category.

How many benchmarks do Mixtral 8x7B and OLMo 2 Furious 13B share?

5 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and OLMo 2 Furious 13B has 12.

Related comparisons

Go deeper