Noometry

Model comparison

GPT-4 vs Qwen2.5 14B Instruct

GPT-4 has enough public results to be ranked (#316); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen2.5 14B Instruct Alibaba (Qwen)

38.7

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen2.5 14B Instruct in 1 category; one gap is clear of the uncertainty.
  • The widest gap is in coding, where Qwen2.5 14B Instruct leads 37.7 to 31.6.
  • The biggest single-benchmark swing is BigCodeBench Instruct: 46% for GPT-4 and 39.8% for Qwen2.5 14B Instruct.
  • Qwen2.5 14B Instruct is cheaper at $0.35 / $1.40 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen2.5 14B Instruct accepts more context: 131K tokens versus 8K.
  • Qwen2.5 14B Instruct has downloadable open weights; the other is API-only.

Side by side

GPT-4Qwen2.5 14B Instruct
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.138.7
Released2023-03-142024-09
WeightsProprietaryOpen
Context window8K131K
Max output8K8K
Input $ / M tokens$30$0.35
Output $ / M tokens$60$1.40
Results tracked383

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

Category by category

Coding Qwen2.5 14B Instruct leads

GPT-4: 31.6 (#283), Qwen2.5 14B Instruct: 37.7 (#191)

BenchmarkGPT-4Qwen2.5 14B Instruct
BigCodeBench Instruct46%39.8%
BigCodeBench Complete57.2%52.2%
WeirdML12.4%—
LMArena Coding1254—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
METR Time Horizons36.1%—

Reasoning Not comparable

GPT-4: 17.8 (#289), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
Chess Puzzles4%—
LMArena Hard Prompts1241—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Not comparable

GPT-4: 10.8 (#309), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
OTIS Mock AIME 2024-20251.1%—
LMArena Math1269—
MATH Level 523%—
GSM8K92%—

Knowledge Not comparable

GPT-4: 18.4 (#282), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
MMLU86.4%79.9%
GPQA Diamond35.7%—
LMArena Expert1211—
TriviaQA84.8%—

Multilingual Not comparable

GPT-4: 40.6 (#215), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
LMArena Non-English1246—
LMArena Chinese1242—
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Russian1251—
LMArena Spanish1261—

Instruction Following Not comparable

GPT-4: 65.3 (#222), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
LMArena Instruction Following1241—

Long Context Not comparable

GPT-4: 37.7 (#212), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
LMArena Longer Query1244—

Writing & Preference Not comparable

GPT-4: 34.9 (#268), Qwen2.5 14B Instruct: —

BenchmarkGPT-4Qwen2.5 14B Instruct
LMArena Text1263—
LMArena Creative Writing1244—
EQ-Bench Creative Writing752—
LMArena Multi-Turn1257—

Frequently asked questions

Is GPT-4 better than Qwen2.5 14B Instruct?

GPT-4 has enough public results to be ranked (#316); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.

Which is cheaper, GPT-4 or Qwen2.5 14B Instruct?

Qwen2.5 14B Instruct is cheaper. It lists at $0.35 per million input tokens and $1.40 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen2.5 14B Instruct better for coding?

Qwen2.5 14B Instruct scores higher on coding benchmarks: 37.7 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen2.5 14B Instruct does, with 131K tokens against 8K.

How many benchmarks do GPT-4 and Qwen2.5 14B Instruct share?

3 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen2.5 14B Instruct has 3.

Related comparisons

Go deeper