Noometry

Model comparison

Deepseek Coder v2 vs Grok 4.20 Multi-Agent

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

Grok 4.20 Multi-Agent xAI

46.2

Rank #65 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Grok 4.20 Multi-Agent in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Grok 4.20 Multi-Agent leads 64.0 to 38.2.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2Grok 4.20 Multi-Agent
ProviderDeepSeekxAI
Noometry Index35.946.2
Released2024-06-172026-03-09
WeightsOpenProprietary
Context window—1M
Max output—30K
Input $ / M tokens—$1.25
Output $ / M tokens—$2.50
Results tracked2420

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

Category by category

Coding Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 38.1 (#183), Grok 4.20 Multi-Agent: 43.0 (#92)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Coding12511457
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, Grok 4.20 Multi-Agent: —

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Search—1204

Reasoning Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 23.6 (#176), Grok 4.20 Multi-Agent: 43.9 (#48)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Hard Prompts12071448
NYT Connections (extended)—89.6%
WinoGrande83.7%—

Math Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 34.9 (#190), Grok 4.20 Multi-Agent: 39.4 (#104)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Math12411442
GSM8K94.5%—

Knowledge Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 32.3 (#212), Grok 4.20 Multi-Agent: 40.4 (#119)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Expert11811445
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, Grok 4.20 Multi-Agent: 40.5 (#48)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Vision—1259

Multilingual Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 36.3 (#240), Grok 4.20 Multi-Agent: 54.4 (#43)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Non-English11821440
LMArena Chinese12011475
LMArena French11851466
LMArena German11641456
LMArena Japanese11261405
LMArena Korean11041416
LMArena Russian11881457
LMArena Spanish11531447

Instruction Following Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 61.7 (#242), Grok 4.20 Multi-Agent: 74.8 (#84)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Instruction Following11801420

Long Context Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 37.0 (#224), Grok 4.20 Multi-Agent: 43.7 (#88)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Longer Query12191431

Writing & Preference Grok 4.20 Multi-Agent leads

Deepseek Coder v2: 38.2 (#253), Grok 4.20 Multi-Agent: 64.0 (#59)

BenchmarkDeepseek Coder v2Grok 4.20 Multi-Agent
LMArena Text11911450
LMArena Creative Writing11201436
LMArena Multi-Turn11771452

Frequently asked questions

Is Deepseek Coder v2 better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or Grok 4.20 Multi-Agent better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and Grok 4.20 Multi-Agent share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Grok 4.20 Multi-Agent has 20.

Related comparisons

Go deeper