Noometry

Model comparison

Deepseek Coder v2 vs GPT-6.1 Sol

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 35.9 on the Noometry Index.

Last verified . 12 shared benchmarks.

Deepseek Coder v2 DeepSeek

35.9

Rank #220 Confirmed

GPT-6.1 Sol OpenAI

65.6

Rank #6 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and GPT-6.1 Sol in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 34.9.
  • Deepseek Coder v2 has downloadable open weights; the other is API-only.

Side by side

Deepseek Coder v2GPT-6.1 Sol
ProviderDeepSeekOpenAI
Noometry Index35.965.6
Released2024-06-172026-09-29
WeightsOpenProprietary
Context window—1.05M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked2434

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

Category by category

Coding GPT-6.1 Sol leads

Deepseek Coder v2: 38.1 (#183), GPT-6.1 Sol: 63.2 (#8)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Coding12511487
DeepSWE—75.2%
FrontierCode—50.2%
LMArena WebDev—1755
SciCode—55.8%
BigCodeBench Instruct48.2%—
BigCodeBench Complete59.7%—
HumanEval+82.3%—
MBPP+75.1%—

Agentic & Tool Use Not comparable

Deepseek Coder v2: —, GPT-6.1 Sol: 39.6 (#26)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
APEX-Agents—60%
GDP.pdf—32%

Reasoning GPT-6.1 Sol leads

Deepseek Coder v2: 23.6 (#176), GPT-6.1 Sol: 81.9 (#2)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Hard Prompts12071466
ARC-AGI-2—94.2%
NYT Connections (extended)—95.5%
ARC-AGI-1—98.5%
CritPt—31.7%
Chess Puzzles—61%
EBR-Bench—54.3%
Mystery Game Puzzles—80%
Epoch Capabilities Index—166.09
WinoGrande83.7%—

Math GPT-6.1 Sol leads

Deepseek Coder v2: 34.9 (#190), GPT-6.1 Sol: 93.7 (#1)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Math12411464
FrontierMath (Tiers 1-3)—93.7%
FrontierMath Tier 4—100%
OTIS Mock AIME 2024-2025—100%
ProofBench—99%
GSM8K94.5%—

Knowledge GPT-6.1 Sol leads

Deepseek Coder v2: 32.3 (#212), GPT-6.1 Sol: 71.8 (#4)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Expert11811502
GPQA Diamond—95.4%
SimpleQA Verified—73.9%
ARC (AI2) Challenge64.3%—

Multimodal Not comparable

Deepseek Coder v2: —, GPT-6.1 Sol: 52.7 (#5)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Vision—1288
Furniture Assembly—80%

Multilingual GPT-6.1 Sol leads

Deepseek Coder v2: 36.3 (#240), GPT-6.1 Sol: 54.3 (#46)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Non-English11821438
LMArena Chinese12011477
LMArena Russian11881455
LMArena French1185—
LMArena German1164—
LMArena Japanese1126—
LMArena Korean1104—
LMArena Spanish1153—

Instruction Following GPT-6.1 Sol leads

Deepseek Coder v2: 61.7 (#242), GPT-6.1 Sol: 77.0 (#29)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Instruction Following11801468

Long Context GPT-6.1 Sol leads

Deepseek Coder v2: 37.0 (#224), GPT-6.1 Sol: 44.9 (#54)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Longer Query12191465

Writing & Preference GPT-6.1 Sol leads

Deepseek Coder v2: 38.2 (#253), GPT-6.1 Sol: 63.6 (#63)

BenchmarkDeepseek Coder v2GPT-6.1 Sol
LMArena Text11911447
LMArena Creative Writing11201432
LMArena Multi-Turn11771449

Frequently asked questions

Is Deepseek Coder v2 better than GPT-6.1 Sol?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 35.9 on the Noometry Index.

Is Deepseek Coder v2 or GPT-6.1 Sol better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 38.1 in the Noometry coding category.

How many benchmarks do Deepseek Coder v2 and GPT-6.1 Sol share?

12 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GPT-6.1 Sol has 34.

Related comparisons

Go deeper