Rankings / Google
Gemini 3.1 Flash Lite Preview
proprietaryreleased 2026-03-03
BenchAtlas Index
as of 2026-09-11
base configuration
rank #288
11 families · 6 categories · high
high effort
rank #300
8 families · 4 categories · medium
Benchmark evidence
53 results
agentic coding
| τ²-Bench | 31.3 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 9.7 % | independent | Artificial Analysis |
coding
| SciCode | 43.4 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 34.7 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 16.0 points | independent | Artificial Analysis | |
| Vals Index | high effort | 15.5 points | independent | Vals AI |
factuality
| MASK contamination=Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. | 48.4 % 47.5–49.3 | independent | Scale Labs |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1477.7 1467.2–1488.2 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1456.9 1451.0–1462.8 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1455.3 1445.8–1464.8 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1454.9 1438.2–1471.7 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1454.2 1449.0–1459.4 | 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 | 1450.8 1444.0–1457.5 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1448.4 1433.2–1463.6 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1444.6 1440.1–1449.2 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1442.5 1433.9–1451.1 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1441.7 1436.0–1447.3 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1440.2 1431.0–1449.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1439.0 1424.7–1453.2 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1438.0 1427.6–1448.4 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1435.7 1429.1–1442.3 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1434.8 1415.3–1454.3 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1433.7 1425.9–1441.5 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1433.4 1428.5–1438.4 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1432.5 1428.8–1436.2 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1431.8 1420.9–1442.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1428.2 1422.8–1433.5 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1427.1 1422.1–1432.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1424.4 1419.8–1429.0 | 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 | 1420.9 1414.5–1427.3 | 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 | 1420.5 1414.5–1426.5 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1419.6 1393.9–1445.3 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1413.1 1406.0–1420.2 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1406.7 1401.3–1412.2 | 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 | 1403.4 1397.0–1409.8 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1401.0 1381.3–1420.6 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond implementation=artificial-analysis | 82.2 % | independent | Artificial Analysis | |
| GPQA Diamond implementation=vals-ai | high effort | 81.1 % | independent | Vals AI |
| Humanity's Last Exam implementation=artificial-analysis | 17.2 % | independent | Artificial Analysis | |
| Humanity's Last Exam contamination=Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. · implementation=scale | 8.6 % 7.5–9.7 | independent | Scale Labs | |
| MMLU-Pro implementation=vals-ai | 86.2 % | independent | Vals AI | |
| MMLU-Pro implementation=vals-ai | high effort | 86.2 % | independent | Vals AI |
long context instruction
| AA-LCR | 74.3 % | independent | Artificial Analysis | |
| IFBench | 77.2 % | independent | Artificial Analysis | |
| MultiChallenge | 60.6 % 60.2–61.0 | independent | Scale Labs |
multimodal
| MMMU implementation=vals-ai | high effort | 82.5 % | independent | Vals AI |
| VISTA | 46.9 % 44.2–49.7 | independent | Scale Labs |
professional
| CaseLaw | high effort | 55.0 % | independent | Vals AI |
| CorpFin | high effort | 59.4 % | independent | Vals AI |
| LegalBench | high effort | 83.8 % | independent | Vals AI |
| TaxEval | high effort | 71.8 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | high effort | 83.3 % | independent | Vals AI |
| EnigmaEval contamination=Potential contamination warning: This model was evaluated after the public release of EnigmaEval, allowing model builder access to the prompts and solutions. | 3.0 % 2.1–4.0 | independent | Scale Labs |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Gemini 3.1 Flash Lite Preview | Terminal-Bench 2.1 | 31.1 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Gemini 3.1 Flash Lite Preview | Terminal-Bench Hard | 24.2 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.
