Noometry

Model comparison

Grok-2 (Dec 2024) vs Qwen2.5 7B Instruct

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.0 on the Noometry Index.

Last verified . 4 shared benchmarks.

Grok-2 (Dec 2024) xAI

33.7

Rank #239 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 4 categories and Qwen2.5 7B Instruct in 2 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Grok-2 (Dec 2024) leads 29.8 to 17.0.
  • The biggest single-benchmark swing is GPQA Diamond: 53.8% for Grok-2 (Dec 2024) and 35.5% for Qwen2.5 7B Instruct.
  • Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.

Side by side

Grok-2 (Dec 2024)Qwen2.5 7B Instruct
ProviderxAIAlibaba (Qwen)
Noometry Index33.729.0
Released2024-08-132024-09
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.17
Output $ / M tokens—$0.70
Results tracked3415

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

Category by category

Coding Qwen2.5 7B Instruct leads

Grok-2 (Dec 2024): 33.3 (#258), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
WeirdML22.2%—
BigCodeBench Instruct—37.6%
LiveBench Coding46.4%—
LMArena Coding1287—
BigCodeBench Complete—46.1%

Agentic & Tool Use Not comparable

Grok-2 (Dec 2024): —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
BALROG—7.8%

Reasoning Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 16.9 (#299), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
DTBench65.2%47.7%
Epoch Capabilities Index130.48118.51
SimpleBench22.7%—
Chess Puzzles—0%
LiveBench Reasoning54.8%—
LMArena Hard Prompts1272—
LiveBench Data Analysis54.5%—
LMCA—6.4%
LiveBench54.3%—

Math Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 20.8 (#284), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
OTIS Mock AIME 2024-202511.5%2.5%
Omni-MATH—29.4%
LiveBench Math54.9%—
LMArena Math1283—
MATH Level 563.5%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 29.8 (#233), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
GPQA Diamond53.8%35.5%
MMLU-Pro—53.9%
Confabulations20.1%—
GPQA (HELM)—34.1%
LMArena Expert1254—
MMLU—72.9%

Multilingual Not comparable

Grok-2 (Dec 2024): 43.1 (#188), Qwen2.5 7B Instruct: —

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
LMArena Non-English1282—
LMArena Chinese1289—
LMArena French1318—
LMArena German1287—
LMArena Japanese1244—
LMArena Korean1237—
LMArena Russian1286—
LMArena Spanish1281—

Instruction Following Grok-2 (Dec 2024) leads

Grok-2 (Dec 2024): 66.9 (#202), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
LiveBench Instruction Following69.6%—
IFEval—74.1%
LMArena Instruction Following1270—

Long Context Not comparable

Grok-2 (Dec 2024): 38.8 (#190), Qwen2.5 7B Instruct: —

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
LMArena Longer Query1276—

Writing & Preference Too close to call

Grok-2 (Dec 2024): 48.6 (#198), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkGrok-2 (Dec 2024)Qwen2.5 7B Instruct
LMArena Text1305—
LMArena Creative Writing1284—
Short-Story Creative Writing63.6%—
WildBench—73.1%
LMArena Multi-Turn1290—
LiveBench Language45.6%—

Frequently asked questions

Is Grok-2 (Dec 2024) better than Qwen2.5 7B Instruct?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.7 to 29.0 on the Noometry Index.

Is Grok-2 (Dec 2024) or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 33.3 in the Noometry coding category.

How many benchmarks do Grok-2 (Dec 2024) and Qwen2.5 7B Instruct share?

4 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper