Noometry

Model comparison

Phi 3 Mini 4k Instruct vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.8 to 27.9 on the Noometry Index.

Last verified . 25 shared benchmarks.

Phi 3 Mini 4k Instruct Microsoft

27.9

Rank #328 Confirmed

QwQ-32B Alibaba (Qwen)

39.8

Rank #159 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where QwQ-32B leads 72.6 to 47.7.
  • The biggest single-benchmark swing is LiveBench Math: 15.7% for Phi 3 Mini 4k Instruct and 77.8% for QwQ-32B.

Side by side

Phi 3 Mini 4k InstructQwQ-32B
ProviderMicrosoftAlibaba (Qwen)
Noometry Index27.939.8
Released2024-04-232024-11-28
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3536

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

Category by category

Coding QwQ-32B leads

Phi 3 Mini 4k Instruct: 26.6 (#323), QwQ-32B: 35.4 (#226)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LiveBench Coding15.5%72.2%
LMArena Coding10931333
Aider Polyglot—20.9%
BigCodeBench Instruct—44.6%
BigCodeBench Complete—54.4%
HumanEval+59.1%—
MBPP+54.2%—

Reasoning QwQ-32B leads

Phi 3 Mini 4k Instruct: 14.1 (#328), QwQ-32B: 23.7 (#174)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
Chess Puzzles0%5%
LiveBench Reasoning26.8%83.5%
LMArena Hard Prompts10721325
LiveBench Data Analysis34.7%65%
LiveBench22.4%72%
Adversarial NLI52.8%—
BIG-Bench Hard71.7%—
Epoch Capabilities Index—137.6
ForecastBench—58.3
HellaSwag76.7%—
WinoGrande70.8%—

Math QwQ-32B leads

Phi 3 Mini 4k Instruct: 26.6 (#257), QwQ-32B: 38.0 (#143)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LiveBench Math15.7%77.8%
LMArena Math11111359
OTIS Mock AIME 2024-2025—59.2%

Knowledge QwQ-32B leads

Phi 3 Mini 4k Instruct: 28.5 (#246), QwQ-32B: 37.2 (#158)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LMArena Expert10451324
GPQA Diamond—65.3%
Confabulations—15.6%
ARC (AI2) Challenge84.9%—
MMLU68.8%—
OpenBookQA88%—
TriviaQA64%—

Multilingual QwQ-32B leads

Phi 3 Mini 4k Instruct: 26.3 (#280), QwQ-32B: 44.8 (#176)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LMArena Non-English10211305
LMArena Chinese10211378
LMArena French10761336
LMArena German10441313
LMArena Japanese9351262
LMArena Korean9051279
LMArena Russian10221297
LMArena Spanish10851354

Instruction Following QwQ-32B leads

Phi 3 Mini 4k Instruct: 47.7 (#303), QwQ-32B: 72.6 (#137)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LiveBench Instruction Following39.1%81.8%
LMArena Instruction Following10531297

Long Context QwQ-32B leads

Phi 3 Mini 4k Instruct: 31.7 (#276), QwQ-32B: 49.0 (#11)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LMArena Longer Query10441308
Fiction.LiveBench—83.3%

Writing & Preference QwQ-32B leads

Phi 3 Mini 4k Instruct: 27.6 (#300), QwQ-32B: 50.6 (#180)

BenchmarkPhi 3 Mini 4k InstructQwQ-32B
LMArena Text10731329
LMArena Creative Writing10371288
LMArena Multi-Turn10181314
LiveBench Language9.2%51.4%
Short-Story Creative Writing—80.2%
EQ-Bench Creative Writing—1257

Frequently asked questions

Is Phi 3 Mini 4k Instruct better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.8 to 27.9 on the Noometry Index.

Is Phi 3 Mini 4k Instruct or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 35.4 versus 26.6 in the Noometry coding category.

How many benchmarks do Phi 3 Mini 4k Instruct and QwQ-32B share?

25 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper