Rankings / Google
Gemma 4 26B A4b
open weightsreleased 2026-04-02
BenchAtlas Index
as of 2026-07-14
thinking
rank #260
7 families · 4 categories · medium
no reasoning
rank #306
7 families · 4 categories · medium
Benchmark evidence
33 results
agentic coding
| τ²-Bench | thinking | 43.6 % | independent | Artificial Analysis |
| τ²-Bench | no reasoning | 40.4 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | thinking | 11.8 % | independent | Artificial Analysis |
coding
| SciCode | thinking | 40.0 % | independent | Artificial Analysis |
| SciCode | no reasoning | 37.3 % | independent | Artificial Analysis |
external indices
| AA Coding Index | thinking | 39.3 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | thinking | 25.7 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 20.1 points | independent | Artificial Analysis |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1479.7 1464.3–1494.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1474.5 1462.1–1486.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1467.8 1453.0–1482.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1461.0 1450.9–1471.2 | 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 | 1451.4 1432.1–1470.7 | 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 | 1449.2 1431.6–1466.8 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1448.6 1434.1–1463.1 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1448.5 1437.1–1459.9 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1446.9 1426.0–1467.9 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1446.9 1429.4–1464.4 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1438.9 1424.8–1453.0 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1438.2 1430.5–1445.8 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1435.1 1423.9–1446.3 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1425.2 1415.2–1435.2 | 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 | 1410.6 1392.6–1428.6 | 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 | 1409.5 1393.9–1425.2 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1402.6 1383.6–1421.5 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | thinking | 79.2 % | independent | Artificial Analysis |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 71.4 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | thinking | 18.3 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 10.7 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | thinking | 55.7 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 39.7 % | independent | Artificial Analysis |
| IFBench | thinking | 72.5 % | independent | Artificial Analysis |
| IFBench | no reasoning | 45.4 % | independent | Artificial Analysis |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Gemma 4 26B A4b | Terminal-Bench 2.1 | 39.0 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Gemma 4 26B A4b | Terminal-Bench Hard | 25.0 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Gemma 4 26B A4b | Terminal-Bench Hard | 13.6 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.