Noometry

Model comparison

Claude 3 Opus vs Tulu 3 (Tülu 3) 70B

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.5 on the Noometry Index.

Last verified . 14 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 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 Opus scores higher in 4 categories and Tulu 3 (Tülu 3) 70B in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Tulu 3 (Tülu 3) 70B leads 23.9 to 14.6.
  • The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus 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 OpusTulu 3 (Tülu 3) 70B
ProviderAnthropicAllen Institute for AI (Ai2)
Noometry Index29.533.0
Released2024-02-292024-11-21
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4614

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

Claude 3 Opus: 32.9 (#267), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Coding12641235
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.6 (#116), Tulu 3 (Tülu 3) 70B: —

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
Cybench10%—
METR Time Horizons29.5%—

Reasoning Tulu 3 (Tülu 3) 70B leads

Claude 3 Opus: 14.6 (#324), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Hard Prompts12451220
SimpleBench23.5%—
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math Too close to call

Claude 3 Opus: 14.8 (#299), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-20254.7%4.4%
LMArena Math12731242
MATH Level 537.5%42.7%
LiveBench Math43.6%—

Knowledge Too close to call

Claude 3 Opus: 24.5 (#267), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
GPQA Diamond47.2%46.3%
SimpleQA Verified12.6%—
Confabulations22.7%—
LMArena Expert1223—
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), Tulu 3 (Tülu 3) 70B: —

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Vision1023—

Multilingual Claude 3 Opus leads

Claude 3 Opus: 41.4 (#207), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Non-English12581236
LMArena Chinese12481249
LMArena Russian12801246
LMArena French1275—
LMArena German1258—
LMArena Japanese1204—
LMArena Korean1187—
LMArena Spanish1246—

Instruction Following Too close to call

Claude 3 Opus: 64.1 (#228), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Instruction Following12481233
LiveBench Instruction Following63.9%—

Long Context Claude 3 Opus leads

Claude 3 Opus: 38.2 (#202), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Longer Query12591224

Writing & Preference Claude 3 Opus leads

Claude 3 Opus: 47.2 (#213), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkClaude 3 OpusTulu 3 (Tülu 3) 70B
LMArena Text12621256
LMArena Creative Writing12351231
LMArena Multi-Turn12751252
LiveBench Language50.4%—

Frequently asked questions

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

Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.5 on the Noometry Index.

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

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 32.9 in the Noometry coding category.

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

14 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper