Rankings / Google DeepMind
Gemma 4 31B
open weightsreleased 2026-04-02
BenchAtlas Index
as of 2026-07-14
thinking
rank #227
7 families · 4 categories · medium
no reasoning
rank #271
7 families · 4 categories · medium
Benchmark evidence
35 results
agentic coding
| τ²-Bench | no reasoning | 65.5 % | independent | Artificial Analysis |
| τ²-Bench | thinking | 59.9 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | thinking | 15.1 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | no reasoning | 8.4 % | independent | Artificial Analysis |
coding
| SciCode | thinking | 43.4 % | independent | Artificial Analysis |
| SciCode | no reasoning | 41.1 % | independent | Artificial Analysis |
external indices
| AA Coding Index | thinking | 43.4 points | independent | Artificial Analysis |
| AA Coding Index | no reasoning | 33.2 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | thinking | 29.4 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 21.8 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1497.6 1482.2–1513.1 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1489.8 1477.5–1502.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1483.0 1468.3–1497.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1473.3 1463.3–1483.2 | 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 | 1471.8 1452.4–1491.3 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1468.0 1445.5–1490.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1467.1 1453.2–1481.1 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1464.9 1447.2–1482.7 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1459.8 1448.5–1471.0 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1454.1 1442.9–1465.2 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1452.2 1438.1–1466.3 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1451.2 1443.6–1458.8 | 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 | 1443.9 1426.8–1461.0 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1439.5 1429.4–1449.5 | 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 | 1434.7 1418.8–1450.6 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1421.3 1402.0–1440.6 | 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 | 1415.2 1397.1–1433.3 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 85.7 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 76.3 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 22.7 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 11.5 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 62.0 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 36.0 % | independent | Artificial Analysis |
| IFBench | thinking | 75.6 % | independent | Artificial Analysis |
| IFBench | no reasoning | 53.5 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Gemma 4 31B | Terminal-Bench 2.1 | 43.5 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Gemma 4 31B | Terminal-Bench Hard | 36.4 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Gemma 4 31B | Terminal-Bench Hard | 30.3 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Gemma 4 31B | Terminal-Bench 2.1 | 29.2 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.