Noometry

DeepSeek, open weights

Deepseek Coder v2

Deepseek Coder v2 by DeepSeek ranks 220th of 354 ranked models on the Noometry Index as of October 2026, with a score of 35.9. Its strongest category is reasoning, where it ranks 176th.

Last verified

Noometry rank
#220 of 354
Index score
35.9
Evidence
Confirmed 24 results
Provider
DeepSeek
Released
June 17, 2024
Weights
Open weights
Reasoning
Unknown
Context window
—
Max output
—
Input price
Not listed
Output price
Not listed
Blended price
Not listed
Output speed
Not measured
Value
Not ranked
Knowledge cutoff
Unknown

Category scores

Each category score combines every public result we have in that category.

  1. Coding 38.1
  2. Reasoning 23.6
  3. Math 34.9
  4. Knowledge 32.3
  5. Multilingual 36.3
  6. Instruction Following 61.7
  7. Long Context 37.0
  8. Writing & Preference 38.2
CategoryScoreRankResults
Coding38.1#1833
Reasoning23.6#1761
Math34.9#1901
Knowledge32.3#2121
Multilingual36.3#2401
Instruction Following61.7#2421
Long Context37.0#2241
Writing & Preference38.2#2533

Strengths and weaknesses

Categories where Deepseek Coder v2 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Reasoning23.6−0.0#176 of 350, top 51%
Coding38.1−0.6#183 of 340, top 54%
Math34.9−1.7#190 of 327, top 59%

Weakest categories

CategoryScorevs medianRank
Writing & Preference38.2−15.6#253 of 312, top 82%
Multilingual36.3−11.2#240 of 297, top 81%
Instruction Following61.7−9.6#242 of 305, top 80%

Closest competitors

The models ranked just above and below Deepseek Coder v2. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Grok Build 0.1#21636.4$1.25—Compare
gpt-oss-120b#21736.3$0.070355Compare
Mistral Medium#21836.3$368Compare
GPT-4.1#21935.9$3.50116Compare
C4ai Aya Expanse 32b#22135.9——Compare
Llama 3.1 Nemotron 51b Instruct#22235.9——Compare
Nemotron 4 340b Instruct#22335.9——Compare
Llama 3.1 Tulu 3 8b#22435.7——Compare

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

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
BigCodeBench Instruct48.2%#8 of 64, top 13%BigCodeBench2024-06-17
LMArena Coding1251#225 of 294, top 77%LMArena2026-10-08
BigCodeBench Complete59.7%#5 of 66, top 8%BigCodeBench2024-06-17
HumanEval+82.3%#9 of 45, top 20%EvalPlus
MBPP+75.1%#4 of 38, top 11%EvalPlus

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1207#234 of 297, top 79%LMArena2026-10-08
WinoGrande83.7%#8 of 43, top 19%Epoch AI

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1241#219 of 285, top 77%LMArena2026-10-08
GSM8K85.8%Epoch AI
GSM8K94.5%Best of 38Epoch AI

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1181#226 of 273, top 83%LMArena2026-10-08
ARC (AI2) Challenge64.3%#20 of 39, top 52%Epoch AI

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1182#240 of 297, top 81%LMArena2026-10-08
LMArena Chinese1201#233 of 285, top 82%LMArena2026-10-08
LMArena French1185#196 of 223, top 88%LMArena2026-10-08
LMArena German1164#200 of 231, top 87%LMArena2026-10-08
LMArena Japanese1126#182 of 211, top 87%LMArena2026-10-08
LMArena Korean1104#189 of 213, top 89%LMArena2026-10-08
LMArena Russian1188#239 of 283, top 85%LMArena2026-10-08
LMArena Spanish1153#203 of 226, top 90%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1180#243 of 298, top 82%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1219#234 of 291, top 81%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1191#246 of 297, top 83%LMArena2026-10-08
LMArena Creative Writing1120#259 of 295, top 88%LMArena2026-10-08
LMArena Multi-Turn1177#244 of 295, top 83%LMArena2026-10-08

Compare Deepseek Coder v2

Other DeepSeek models

Frequently asked questions

How good is Deepseek Coder v2?

Deepseek Coder v2 by DeepSeek ranks 220th of 354 ranked models on the Noometry Index as of October 2026, with a score of 35.9. Its strongest category is reasoning, where it ranks 176th.

Is Deepseek Coder v2 open source?

Yes. Deepseek Coder v2's weights are downloadable; check the license for commercial terms.

What are Deepseek Coder v2's strengths and weaknesses?

Relative to other ranked models, Deepseek Coder v2 places best in reasoning, coding, math and lowest in writing & preference, multilingual, instruction following.

What is Deepseek Coder v2 best at?

Its best category is reasoning, where it ranks 176th on Noometry.