Noometry

Model comparison

Llama 3.1-70B vs Tulu 3 (Tülu 3) 70B

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.

Last verified . 14 shared benchmarks.

Llama 3.1-70B Meta

29.6

Rank #308 Confirmed

Tulu 3 (Tülu 3) 70B Allen Institute for AI (Ai2)

33.0

Rank #251 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Llama 3.1-70B scores higher in 2 categories and Tulu 3 (Tülu 3) 70B in 6 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 35.4.
  • The biggest single-benchmark swing is MATH Level 5: 36.7% for Llama 3.1-70B and 42.7% for Tulu 3 (Tülu 3) 70B.

Side by side

Llama 3.1-70BTulu 3 (Tülu 3) 70B
ProviderMetaAllen Institute for AI (Ai2)
Noometry Index29.633.0
Released2024-07-232024-11-21
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.40—
Output $ / M tokens$0.40—
Results tracked3514

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

Llama 3.1-70B: 30.3 (#296), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
LMArena Coding12601235
WeirdML9%—
BigCodeBench Instruct46.1%—
BigCodeBench Complete54.8%—

Agentic & Tool Use Not comparable

Llama 3.1-70B: 25.1 (#112), Tulu 3 (Tülu 3) 70B: —

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
TheAgentCompany6.9%—
BALROG27.9%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Llama 3.1-70B: 21.6 (#220), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
LMArena Hard Prompts12411220
DTBench60%—
LMCA14.8%—
Epoch Capabilities Index125.92—

Math Too close to call

Llama 3.1-70B: 13.5 (#304), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-20253.6%4.4%
LMArena Math12521242
MATH Level 536.7%42.7%
Omni-MATH21%—

Knowledge Too close to call

Llama 3.1-70B: 24.2 (#269), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
GPQA Diamond44.2%46.3%
MMLU-Pro65.3%—
GPQA (HELM)42.6%—
LMArena Expert1209—
MMLU80.1%—

Multilingual Tulu 3 (Tülu 3) 70B leads

Llama 3.1-70B: 38.8 (#225), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
LMArena Non-English12191236
LMArena Chinese12151249
LMArena Russian12341246
LMArena French1261—
LMArena German1222—
LMArena Japanese1132—
LMArena Korean1140—
LMArena Spanish1253—

Instruction Following Too close to call

Llama 3.1-70B: 65.3 (#223), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
LMArena Instruction Following12311233
IFEval82.1%—

Long Context Too close to call

Llama 3.1-70B: 37.6 (#214), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
LMArena Longer Query12411224

Writing & Preference Tulu 3 (Tülu 3) 70B leads

Llama 3.1-70B: 35.4 (#267), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkLlama 3.1-70BTulu 3 (Tülu 3) 70B
LMArena Text12611256
LMArena Creative Writing12321231
LMArena Multi-Turn12561252
EQ-Bench Creative Writing784—
WildBench75.8%—

Frequently asked questions

Is Llama 3.1-70B better than Tulu 3 (Tülu 3) 70B?

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.

Is Llama 3.1-70B or Tulu 3 (Tülu 3) 70B better for coding?

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 30.3 in the Noometry coding category.

How many benchmarks do Llama 3.1-70B and Tulu 3 (Tülu 3) 70B share?

14 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper