Noometry

Model comparison

Claude Sonnet 4 vs Tulu 3 (Tülu 3) 70B

Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 32.6 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude Sonnet 4 Anthropic

40.6

Rank #139 Confirmed

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

32.6

Rank #242 Confirmed

Summary

  • They share 14 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4 leads 41.5 to 13.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 4.4% for Tulu 3 (Tülu 3) 70B.
  • Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4Tulu 3 (Tülu 3) 70B
ProviderAnthropicAllen Institute for AI (Ai2)
Noometry Index40.632.6
Released2025-05-222024-11-21
WeightsProprietaryOpen
Context window200K—
Max output64K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked5814

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

Category by category

Coding Claude Sonnet 4 leads

Claude Sonnet 4: 44.0 (#70), Tulu 3 (Tülu 3) 70B: 35.4 (#211)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Coding14141236
SWE-bench Verified (bash only)64.9%—
Aider Polyglot61.3%—
SciCode40%—
GSO4.9%—
WeirdML46.1%—
ALE-Bench655.35—

Agentic & Tool Use Not comparable

Claude Sonnet 4: 38.3 (#29), Tulu 3 (Tülu 3) 70B: —

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
TheAgentCompany33.1%—
Cybench35%—
DeepResearch Bench46.6%—
OSWorld43.9%—
METR Time Horizons62%—

Reasoning Too close to call

Claude Sonnet 4: 23.0 (#169), Tulu 3 (Tülu 3) 70B: 22.9 (#172)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Hard Prompts13721220
ARC-AGI-25.9%—
SimpleBench45.5%—
Kagi LLM Benchmark73%—
ARC-AGI-140%—
CritPt0.3%—
EnigmaEval3.1%—
DTBench77.1%—
LMCA29%—
Epoch Capabilities Index141.69—
ForecastBench60.2—

Math Claude Sonnet 4 leads

Claude Sonnet 4: 41.5 (#71), Tulu 3 (Tülu 3) 70B: 13.3 (#297)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202571.1%4.4%
LMArena Math13751242
MATH Level 584.4%42.7%
Omni-MATH60.2%—
FrontierMath (Feb 2025 set)4.1%—
FrontierMath Tier 4 (v1)0%—

Knowledge Claude Sonnet 4 leads

Claude Sonnet 4: 41.6 (#99), Tulu 3 (Tülu 3) 70B: 25.1 (#257)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
GPQA Diamond79.2%46.3%
Humanity's Last Exam7.8%—
MMLU-Pro84.3%—
Confabulations13.2%—
Vectara Hallucination Rate10.3%—
GPQA (HELM)70.6%—
LMArena Expert1371—

Multimodal Not comparable

Claude Sonnet 4: 25.6 (#116), Tulu 3 (Tülu 3) 70B: —

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Vision1191—
GeoBench37%—
VPCT34%—
MindCube44.8%—

Multilingual Claude Sonnet 4 leads

Claude Sonnet 4: 46.9 (#151), Tulu 3 (Tülu 3) 70B: 40.1 (#217)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Non-English13331236
LMArena Chinese13511249
LMArena Russian13551246
LMArena French1364—
LMArena German1331—
LMArena Japanese1301—
LMArena Korean1293—
LMArena Spanish1356—

Instruction Following Claude Sonnet 4 leads

Claude Sonnet 4: 71.8 (#141), Tulu 3 (Tülu 3) 70B: 65.0 (#222)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Instruction Following13751233
IFEval84%—

Long Context Tulu 3 (Tülu 3) 70B leads

Claude Sonnet 4: 33.6 (#254), Tulu 3 (Tülu 3) 70B: 37.1 (#217)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Longer Query13981224
Fiction.LiveBench46.9%—

Writing & Preference Claude Sonnet 4 leads

Claude Sonnet 4: 57.3 (#127), Tulu 3 (Tülu 3) 70B: 45.8 (#218)

BenchmarkClaude Sonnet 4Tulu 3 (Tülu 3) 70B
LMArena Text13511256
LMArena Creative Writing13451231
LMArena Multi-Turn13761252
Short-Story Creative Writing81.4%—
EQ-Bench Creative Writing1483—
WildBench83.8%—

Frequently asked questions

Is Claude Sonnet 4 better than Tulu 3 (Tülu 3) 70B?

Claude Sonnet 4 is the stronger model overall, scoring 40.6 to 32.6 on the Noometry Index.

Is Claude Sonnet 4 or Tulu 3 (Tülu 3) 70B better for coding?

Claude Sonnet 4 scores higher on coding benchmarks: 44.0 versus 35.4 in the Noometry coding category.

How many benchmarks do Claude Sonnet 4 and Tulu 3 (Tülu 3) 70B share?

14 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper