Noometry

Model comparison

Qwen3.5-Flash vs Tulu 3 (Tülu 3) 70B

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 33.0 on the Noometry Index.

Last verified . 13 shared benchmarks.

Qwen3.5-Flash Alibaba (Qwen)

42.5

Rank #112 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. Qwen3.5-Flash scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.5-Flash leads 37.4 to 14.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 84.4% for Qwen3.5-Flash 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

Qwen3.5-FlashTulu 3 (Tülu 3) 70B
ProviderAlibaba (Qwen)Allen Institute for AI (Ai2)
Noometry Index42.533.0
Released2026-02-232024-11-21
WeightsProprietaryOpen
Context window1M—
Max output66K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.40—
Results tracked3214

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

Category by category

Coding Tulu 3 (Tülu 3) 70B leads

Qwen3.5-Flash: 34.2 (#242), Tulu 3 (Tülu 3) 70B: 36.0 (#214)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
LMArena Coding14121235
LMArena WebDev1244—
ALE-Bench221.8—

Agentic & Tool Use Not comparable

Qwen3.5-Flash: —, Tulu 3 (Tülu 3) 70B: —

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
Vending-Bench 2462.69—

Reasoning Qwen3.5-Flash leads

Qwen3.5-Flash: 33.7 (#72), Tulu 3 (Tülu 3) 70B: 23.9 (#169)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
LMArena Hard Prompts14031220
Chess Puzzles21%—
Mystery Game Puzzles20%—
DTBench82.9%—
LMCA29.1%—
Epoch Capabilities Index143.98—

Math Qwen3.5-Flash leads

Qwen3.5-Flash: 37.4 (#158), Tulu 3 (Tülu 3) 70B: 14.2 (#303)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
OTIS Mock AIME 2024-202584.4%4.4%
LMArena Math14071242
FrontierMath (Tiers 1-3)18.2%—
MATH Level 5—42.7%
FrontierMath (Feb 2025 set)6.2%—
FrontierMath Tier 4 (v1)0%—

Knowledge Qwen3.5-Flash leads

Qwen3.5-Flash: 43.2 (#93), Tulu 3 (Tülu 3) 70B: 25.0 (#264)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
GPQA Diamond82.3%46.3%
SimpleQA Verified20.3%—
Vectara Hallucination Rate10.5%—
LMArena Expert1407—

Multilingual Qwen3.5-Flash leads

Qwen3.5-Flash: 50.5 (#121), Tulu 3 (Tülu 3) 70B: 39.9 (#222)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
LMArena Non-English13851236
LMArena Chinese14461249
LMArena Russian13791246
LMArena French1412—
LMArena German1390—
LMArena Japanese1368—
LMArena Korean1344—
LMArena Spanish1400—

Instruction Following Qwen3.5-Flash leads

Qwen3.5-Flash: 72.6 (#139), Tulu 3 (Tülu 3) 70B: 64.8 (#227)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
LMArena Instruction Following13741233

Long Context Qwen3.5-Flash leads

Qwen3.5-Flash: 42.4 (#124), Tulu 3 (Tülu 3) 70B: 37.1 (#222)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
LMArena Longer Query13921224

Writing & Preference Qwen3.5-Flash leads

Qwen3.5-Flash: 57.9 (#122), Tulu 3 (Tülu 3) 70B: 45.6 (#223)

BenchmarkQwen3.5-FlashTulu 3 (Tülu 3) 70B
LMArena Text13971256
LMArena Creative Writing13431231
LMArena Multi-Turn13931252

Frequently asked questions

Is Qwen3.5-Flash better than Tulu 3 (Tülu 3) 70B?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 33.0 on the Noometry Index.

Is Qwen3.5-Flash or Tulu 3 (Tülu 3) 70B better for coding?

Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 34.2 in the Noometry coding category.

How many benchmarks do Qwen3.5-Flash and Tulu 3 (Tülu 3) 70B share?

13 benchmarks have published results for both models. Qwen3.5-Flash has 32 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.

Related comparisons

Go deeper