Noometry

Model comparison

Claude 3 Haiku vs Tulu 3 (Tülu 3) 70B

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 25.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 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 Haiku scores higher in 0 categories and Tulu 3 (Tülu 3) 70B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Tulu 3 (Tülu 3) 70B leads 45.6 to 29.7.
  • The biggest single-benchmark swing is MATH Level 5: 14.9% for Claude 3 Haiku 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 HaikuTulu 3 (Tülu 3) 70B
ProviderAnthropicAllen Institute for AI (Ai2)
Noometry Index25.933.0
Released2024-03-072024-11-21
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3714

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 26.4 (#325), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Coding11991235
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 16.3 (#307), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Hard Prompts11741220
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
ForecastBench53.2—
WinoGrande74.2%—

Math Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 9.8 (#319), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-20251.8%4.4%
LMArena Math11881242
MATH Level 514.9%42.7%

Knowledge Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 17.3 (#285), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
GPQA Diamond36.3%46.3%
Confabulations34.2%—
LMArena Expert1148—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Tulu 3 (Tülu 3) 70B: —

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Vision950—
ScienceQA72%—

Multilingual Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 36.0 (#243), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Non-English11781236
LMArena Chinese11551249
LMArena Russian12041246
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Spanish1166—

Instruction Following Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 61.3 (#247), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Instruction Following11731233

Long Context Tulu 3 (Tülu 3) 70B leads

Claude 3 Haiku: 36.1 (#237), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Longer Query11901224

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

Claude 3 Haiku: 29.7 (#291), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkClaude 3 HaikuTulu 3 (Tülu 3) 70B
LMArena Text11951256
LMArena Creative Writing11571231
LMArena Multi-Turn11901252
EQ-Bench Creative Writing717—

Frequently asked questions

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

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 25.9 on the Noometry Index.

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

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 26.4 in the Noometry coding category.

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

14 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper