Noometry

Model comparison

Claude 3 Sonnet vs Tulu 3 (Tülu 3) 70B

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.0 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 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. Claude 3 Sonnet scores higher in 0 categories and Tulu 3 (Tülu 3) 70B in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Tulu 3 (Tülu 3) 70B leads 36.0 to 29.6.
  • The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 42.7% for Tulu 3 (Tülu 3) 70B.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetTulu 3 (Tülu 3) 70B
ProviderAnthropicAllen Institute for AI (Ai2)
Noometry Index29.033.0
Released2024-02-292024-11-21
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3014

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

Claude 3 Sonnet: 29.6 (#302), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Coding12231235
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
HumanEval+64%—
MBPP+69.3%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Claude 3 Sonnet: 20.5 (#237), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Hard Prompts11971220
DTBench53.6%—
Epoch Capabilities Index120.7—
WinoGrande75.1%—

Math Tulu 3 (Tülu 3) 70B leads

Claude 3 Sonnet: 10.7 (#310), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-20252.5%4.4%
LMArena Math12131242
MATH Level 518.2%42.7%

Knowledge Tulu 3 (Tülu 3) 70B leads

Claude 3 Sonnet: 21.1 (#276), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
GPQA Diamond40.6%46.3%
LMArena Expert1173—
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), Tulu 3 (Tülu 3) 70B: —

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Vision984—

Multilingual Tulu 3 (Tülu 3) 70B leads

Claude 3 Sonnet: 37.8 (#234), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Non-English12051236
LMArena Chinese11891249
LMArena Russian12271246
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Spanish1204—

Instruction Following Tulu 3 (Tülu 3) 70B leads

Claude 3 Sonnet: 62.8 (#235), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Instruction Following11991233

Long Context Too close to call

Claude 3 Sonnet: 36.7 (#228), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Longer Query12111224

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

Claude 3 Sonnet: 42.1 (#238), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkClaude 3 SonnetTulu 3 (Tülu 3) 70B
LMArena Text12181256
LMArena Creative Writing11861231
LMArena Multi-Turn12271252

Frequently asked questions

Is Claude 3 Sonnet better than Tulu 3 (Tülu 3) 70B?

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Tulu 3 (Tülu 3) 70B better for coding?

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Tulu 3 (Tülu 3) 70B share?

14 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper