Noometry

Model comparison

Qwen3.6 Plus vs Tulu 3 (Tülu 3) 70B

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 33.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

Qwen3.6 Plus Alibaba (Qwen)

47.5

Rank #62 Confirmed

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

33.0

Rank #251 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Qwen3.6 Plus scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for Qwen3.6 Plus 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

Qwen3.6 PlusTulu 3 (Tülu 3) 70B
ProviderAlibaba (Qwen)Allen Institute for AI (Ai2)
Noometry Index47.533.0
Released2026-03-312024-11-21
WeightsProprietaryOpen
Context window1M—
Max output66K—
Input $ / M tokens$0.50—
Output $ / M tokens$3—
Results tracked3714

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

Category by category

Coding Qwen3.6 Plus leads

Qwen3.6 Plus: 40.8 (#130), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
LMArena Coding14671235
SWE-bench Verified57.9%—
LMArena WebDev1461—
SciCode40.7%—
ALE-Bench670.15—

Agentic & Tool Use Not comparable

Qwen3.6 Plus: —, Tulu 3 (Tülu 3) 70B: —

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
Vending-Bench 25,115—

Reasoning Qwen3.6 Plus leads

Qwen3.6 Plus: 29.3 (#93), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
LMArena Hard Prompts14491220
NYT Connections (extended)60.3%—
CritPt2.9%—
Chess Puzzles17%—
Thematic Generalization59.5%—
Mystery Game Puzzles12%—
DTBench81.9%—
LMCA33.1%—
Epoch Capabilities Index147.65—

Math Qwen3.6 Plus leads

Qwen3.6 Plus: 51.8 (#54), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202593.3%4.4%
LMArena Math14501242
FrontierMath (Tiers 1-3)38.2%—
MATH Level 5—42.7%
FrontierMath (Feb 2025 set)26.2%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Qwen3.6 Plus leads

Qwen3.6 Plus: 56.1 (#45), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
GPQA Diamond88.4%46.3%
SimpleQA Verified44.1%—
LMArena Expert1454—

Multilingual Qwen3.6 Plus leads

Qwen3.6 Plus: 53.3 (#70), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
LMArena Non-English14241236
LMArena Chinese14771249
LMArena Russian14341246
LMArena French1455—
LMArena German1452—
LMArena Japanese1389—
LMArena Korean1379—
LMArena Spanish1432—

Instruction Following Qwen3.6 Plus leads

Qwen3.6 Plus: 75.0 (#74), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
LMArena Instruction Following14251233

Long Context Qwen3.6 Plus leads

Qwen3.6 Plus: 45.2 (#49), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
LMArena Longer Query14391224
CL-bench20.3%—

Writing & Preference Qwen3.6 Plus leads

Qwen3.6 Plus: 62.2 (#82), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkQwen3.6 PlusTulu 3 (Tülu 3) 70B
LMArena Text14371256
LMArena Creative Writing14041231
LMArena Multi-Turn14381252

Frequently asked questions

Is Qwen3.6 Plus better than Tulu 3 (Tülu 3) 70B?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 33.0 on the Noometry Index.

Is Qwen3.6 Plus or Tulu 3 (Tülu 3) 70B better for coding?

Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 36.0 in the Noometry coding category.

How many benchmarks do Qwen3.6 Plus and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. Qwen3.6 Plus has 37 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper