Noometry

Model comparison

Grok 4.20 (Non-Reasoning) vs Qwen2.5 72B Instruct

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 31.9 on the Noometry Index.

Last verified . 24 shared benchmarks.

Grok 4.20 (Non-Reasoning) xAI

48.6

Rank #54 Confirmed

Qwen2.5 72B Instruct Alibaba (Qwen)

31.9

Rank #267 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 22.3.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) and 8.1% for Qwen2.5 72B Instruct.
  • Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
  • Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 131K.
  • Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Grok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
ProviderxAIAlibaba (Qwen)
Noometry Index48.631.9
Released2026-02-172024-09
WeightsProprietaryOpen
Context window1M131K
Max output30K8K
Input $ / M tokens$1.25$1.40
Output $ / M tokens$2.50$5.60
Results tracked4643

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

Category by category

Coding Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen2.5 72B Instruct: 33.2 (#260)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
WeirdML52.3%16%
LMArena Coding14591292
LMArena WebDev1375—
BigCodeBench Instruct—45.8%
BigCodeBench Complete—55.9%
ALE-Bench1,150—

Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen2.5 72B Instruct: 22.1 (#133)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
Terminal-Bench57.3%—
TheAgentCompany—5.7%
τ²-bench Banking18%—
BALROG—16.2%
LMArena Search1189—
METR Time Horizons—35.8%
Vending-Bench 24,663—

Reasoning Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.3 (#32), Qwen2.5 72B Instruct: 22.3 (#199)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
LMArena Hard Prompts14511271
DTBench90.1%62.9%
LMCA38.7%13.4%
Epoch Capabilities Index151.98129
ForecastBench61.457.5
ARC-AGI-265.1%—
Kagi LLM Benchmark75%—
NYT Connections (extended)85.4%—
ARC-AGI-189.5%—
Chess Puzzles24%—
Thematic Generalization63.8%—
BIG-Bench Hard—79.8%
HellaSwag—84.8%
PIQA—82.6%
WinoGrande—82.3%

Math Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen2.5 72B Instruct: 19.3 (#287)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
OTIS Mock AIME 2024-202592.2%8.1%
LMArena Math14551283
FrontierMath (Tiers 1-3)44.9%—
FrontierMath Tier 417.1%—
ProofBench14%—
Omni-MATH—33%
MATH Level 5—63.2%

Knowledge Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen2.5 72B Instruct: 27.0 (#253)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
GPQA Diamond89.3%49.1%
LMArena Expert14391245
SimpleQA Verified30.2%—
MMLU-Pro—63.1%
Confabulations—19.1%
GPQA (HELM)—42.6%
ARC (AI2) Challenge—94.5%
MMLU—85.3%
TriviaQA—71.9%

Multimodal Not comparable

Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen2.5 72B Instruct: —

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
LMArena Vision1263—
Blueprint-Bench 20%—
LMArena Document1416—

Multilingual Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen2.5 72B Instruct: 41.0 (#213)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
LMArena Non-English14411252
LMArena Chinese14811272
LMArena French14761280
LMArena German14651234
LMArena Japanese14491180
LMArena Korean14171188
LMArena Russian14581264
LMArena Spanish14431256

Instruction Following Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen2.5 72B Instruct: 65.5 (#221)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
LMArena Instruction Following14201254
IFEval—80.6%

Long Context Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen2.5 72B Instruct: 38.9 (#188)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
LMArena Longer Query14371282
CL-bench22.2%—
CL-bench Life11.9%—

Writing & Preference Grok 4.20 (Non-Reasoning) leads

Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen2.5 72B Instruct: 46.7 (#215)

BenchmarkGrok 4.20 (Non-Reasoning)Qwen2.5 72B Instruct
LMArena Text14511269
LMArena Creative Writing14381221
LMArena Multi-Turn14561272
EQ-Bench Creative Writing1574—
WildBench—80.2%

Frequently asked questions

Is Grok 4.20 (Non-Reasoning) better than Qwen2.5 72B Instruct?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 31.9 on the Noometry Index.

Which is cheaper, Grok 4.20 (Non-Reasoning) or Qwen2.5 72B Instruct?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

Is Grok 4.20 (Non-Reasoning) or Qwen2.5 72B Instruct better for coding?

Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 131K.

How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen2.5 72B Instruct share?

24 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen2.5 72B Instruct has 43.

Related comparisons

Go deeper