Noometry

Model comparison

Qwen1.5-110B vs Qwen3-4B

Qwen1.5-110B is the stronger model overall, scoring 33.6 to 31.5 on the Noometry Index.

Last verified . 0 shared benchmarks.

Qwen1.5-110B Alibaba (Qwen)

33.6

Rank #231 Confirmed

Qwen3-4B Alibaba (Qwen)

31.5

Rank #261 Confirmed

Summary

  • The widest gap is in reasoning, where Qwen1.5-110B leads 21.7 to 18.5.

Side by side

Qwen1.5-110BQwen3-4B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index33.631.5
Released2024-04-252025-04-29
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked206

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

Category by category

Coding Not comparable

Qwen1.5-110B: 32.4 (#260), Qwen3-4B: —

BenchmarkQwen1.5-110BQwen3-4B
BigCodeBench Instruct35%—
LMArena Coding1184—
BigCodeBench Complete44.4%—

Agentic & Tool Use Not comparable

Qwen1.5-110B: —, Qwen3-4B: 27.3 (#94)

BenchmarkQwen1.5-110BQwen3-4B
Berkeley Function Calling Leaderboard—35.7%

Reasoning Qwen1.5-110B leads

Qwen1.5-110B: 21.7 (#192), Qwen3-4B: 18.5 (#264)

BenchmarkQwen1.5-110BQwen3-4B
Chess Puzzles—4%
LMArena Hard Prompts1168—
ForecastBench57.7—

Math Qwen1.5-110B leads

Qwen1.5-110B: 31.1 (#199), Qwen3-4B: 28.5 (#228)

BenchmarkQwen1.5-110BQwen3-4B
MathArena Final-Answer Competitions—38.5%
OTIS Mock AIME 2024-2025—52.2%
LMArena Math1185—

Knowledge Qwen3-4B leads

Qwen1.5-110B: 30.7 (#217), Qwen3-4B: 33.0 (#198)

BenchmarkQwen1.5-110BQwen3-4B
GPQA Diamond—52.3%
Vectara Hallucination Rate—5.7%
LMArena Expert1144—

Multilingual Not comparable

Qwen1.5-110B: 33.8 (#245), Qwen3-4B: —

BenchmarkQwen1.5-110BQwen3-4B
LMArena Non-English1142—
LMArena Chinese1206—
LMArena French1150—
LMArena German1123—
LMArena Japanese1074—
LMArena Korean1044—
LMArena Russian1118—
LMArena Spanish1141—

Instruction Following Not comparable

Qwen1.5-110B: 60.6 (#247), Qwen3-4B: —

BenchmarkQwen1.5-110BQwen3-4B
LMArena Instruction Following1158—

Long Context Not comparable

Qwen1.5-110B: 35.0 (#237), Qwen3-4B: —

BenchmarkQwen1.5-110BQwen3-4B
LMArena Longer Query1157—

Writing & Preference Not comparable

Qwen1.5-110B: 38.1 (#250), Qwen3-4B: —

BenchmarkQwen1.5-110BQwen3-4B
LMArena Text1175—
LMArena Creative Writing1148—
LMArena Multi-Turn1160—

Frequently asked questions

Is Qwen1.5-110B better than Qwen3-4B?

Qwen1.5-110B is the stronger model overall, scoring 33.6 to 31.5 on the Noometry Index.

How many benchmarks do Qwen1.5-110B and Qwen3-4B share?

0 benchmarks have published results for both models. Qwen1.5-110B has 20 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper