Noometry

Model comparison

Grok-3 mini vs Qwen2.5 7B Instruct

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.0 on the Noometry Index.

Last verified . 8 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • They share 8 benchmarks with published results for both. Grok-3 mini scores higher in 5 categories and Qwen2.5 7B Instruct in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 42.1 to 12.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 2.5% for Qwen2.5 7B Instruct.
  • Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniQwen2.5 7B Instruct
ProviderxAIAlibaba (Qwen)
Noometry Index41.229.0
Released2025-04-092024-09
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.17
Output $ / M tokens—$0.70
Results tracked3515

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

Category by category

Coding Grok-3 mini leads

Grok-3 mini: 40.8 (#131), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
Aider Polyglot49.3%—
WeirdML42.6%—
BigCodeBench Instruct—37.6%
LMArena Coding1379—
BigCodeBench Complete—46.1%

Agentic & Tool Use Not comparable

Grok-3 mini: —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
BALROG—7.8%

Reasoning Qwen2.5 7B Instruct leads

Grok-3 mini: 13.6 (#334), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
Epoch Capabilities Index140.35118.51
ARC-AGI-20.4%—
Kagi LLM Benchmark61.3%—
ARC-AGI-116.5%—
Chess Puzzles—0%
LMArena Hard Prompts1375—
DTBench—47.7%
LMCA—6.4%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
OTIS Mock AIME 2024-202577.8%2.5%
Omni-MATH31.8%29.4%
LMArena Math1386—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
GPQA Diamond76.3%35.5%
MMLU-Pro79.9%53.9%
GPQA (HELM)67.5%34.1%
Confabulations10.8%—
LMArena Expert1395—
MMLU—72.9%

Multilingual Not comparable

Grok-3 mini: 48.1 (#145), Qwen2.5 7B Instruct: —

BenchmarkGrok-3 miniQwen2.5 7B Instruct
LMArena Non-English1352—
LMArena Chinese1387—
LMArena French1357—
LMArena German1349—
LMArena Japanese1342—
LMArena Korean1335—
LMArena Russian1353—
LMArena Spanish1381—

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
IFEval95.1%74.1%
LMArena Instruction Following1357—

Long Context Not comparable

Grok-3 mini: 41.0 (#147), Qwen2.5 7B Instruct: —

BenchmarkGrok-3 miniQwen2.5 7B Instruct
Fiction.LiveBench66.7%—
LMArena Longer Query1372—

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkGrok-3 miniQwen2.5 7B Instruct
WildBench65.1%73.1%
LMArena Text1370—
LMArena Creative Writing1342—
Short-Story Creative Writing73.5%—
LMArena Multi-Turn1355—

Frequently asked questions

Is Grok-3 mini better than Qwen2.5 7B Instruct?

Grok-3 mini is the stronger model overall, scoring 41.2 to 29.0 on the Noometry Index.

Is Grok-3 mini or Qwen2.5 7B Instruct better for coding?

Grok-3 mini scores higher on coding benchmarks: 40.8 versus 36.5 in the Noometry coding category.

How many benchmarks do Grok-3 mini and Qwen2.5 7B Instruct share?

8 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper