Rankings / DeepSeek
Deepseek V3 2 Exp
released 2025-09-29
BenchAtlas Index
as of 2026-09-11
thinking
rank #229
9 families · 5 categories · high
no reasoning
rank #261
9 families · 5 categories · high
Benchmark evidence
47 results
agentic coding
| τ²-Bench | no reasoning | 33.9 % | independent | Artificial Analysis |
| τ²-Bench | thinking | 33.9 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | thinking | 78.9 % | independent | Artificial Analysis |
| LiveCodeBench v6 implementation=artificial-analysis | no reasoning | 55.4 % | independent | Artificial Analysis |
| SciCode | no reasoning | 39.9 % | independent | Artificial Analysis |
| SciCode | thinking | 37.7 % | independent | Artificial Analysis |
external indices
| Intelligence Index v4.1 | thinking | 16.6 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 13.9 points | independent | Artificial Analysis |
| AA Math Index | thinking | 87.7 points | independent | Artificial Analysis |
| AA Math Index | no reasoning | 57.7 points | independent | Artificial Analysis |
| ECI | high effort | 145.1 points | independent | Epoch AI Benchmarking Hub |
| ECI | 145.1 points | independent | Epoch AI Benchmarking Hub |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1468.0 1449.7–1486.3 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1465.0 1453.2–1476.7 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1452.9 1443.3–1462.5 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1450.2 1438.9–1461.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1446.0 1438.0–1454.0 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1440.0 1429.2–1450.7 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1436.7 1427.9–1445.5 | community | LMArena Leaderboard Dataset | |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1434.8 1421.3–1448.3 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1434.0 1409.8–1458.3 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1428.7 1415.4–1441.9 | community | LMArena Leaderboard Dataset | |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | 1423.0 1410.3–1435.6 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1422.4 1416.0–1428.8 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1419.6 1397.0–1442.3 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1416.5 1395.9–1437.1 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1415.4 1406.4–1424.3 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1414.9 1404.6–1425.2 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1414.3 1391.5–1437.1 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1413.8 1393.3–1434.3 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1412.0 1400.4–1423.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1408.5 1393.8–1423.3 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1407.1 1394.4–1419.7 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1407.0 1399.1–1414.9 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1400.8 1383.8–1417.9 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 79.7 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 73.8 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 14.9 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 9.0 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | thinking | 85.0 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | no reasoning | 83.6 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 72.3 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 44.7 % | independent | Artificial Analysis |
| IFBench | thinking | 54.1 % | independent | Artificial Analysis |
| IFBench | no reasoning | 43.1 % | independent | Artificial Analysis |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | thinking | 87.7 % | independent | Artificial Analysis |
| AIME year=2025 · implementation=artificial-analysis | no reasoning | 57.7 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Deepseek V3 2 Exp | Terminal-Bench Hard | 31.1 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Deepseek V3 2 Exp | Terminal-Bench Hard | 25.0 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.