Gemini 3.1 Flash Lite Preview
| Released | 2026-03-03 |
|---|---|
| Price per 1M | $0.25 in · $1.50 out |
| Overall score | 48.0 · rank 128 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 48.0 | 128 | 16 |
| Overall: Coding | 47.3 | 130 | 9 |
| Overall: Reasoning | 45.8 | 153 | 4 |
| Overall: Agentic work | 48.8 | 122 | 7 |
| Overall: Frontend | 37.6 | 186 | 7 |
| Coding | 52.9 | 95 | 3 |
| Agents | 47.9 | 120 | 2 |
| Reasoning | 45.7 | 148 | 2 |
| Knowledge | 46.0 | 111 | 2 |
| Frontend | 27.2 | 133 | 2 |
| General | 49.2 | 116 | 3 |
| Multimodal | 54.2 | 55 | 2 |
| Value vs price | +2.0 | 107 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 48.9 ±2.9 | 8 |
| High | 47.2 ±2.2 | 8 |
Evidence
Coding 52.9 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 62.8% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 80.1% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 47.9 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.1 (Vals run) | 34.1% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 3.1% | Vals AI | 2026-11-09 |
Reasoning 45.7 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 8.2% | Lech Mazur | 2026-11-10 |
| GPQA Diamond (Vals run) | 81.1% | Vals AI | 2026-09-01 |
Knowledge 46.0 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 86.2% | Vals AI | 2026-09-01 |
| Legal Research Bench | 3.4% | Vals AI | 2026-11-09 |
Frontend 27.2 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 0.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,256 | LMArena | 2026-11-10 |
General 49.2 ±3.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,433 | LMArena | 2026-11-09 |
| LLM Debate Benchmark | 1,322 | Lech Mazur | 2026-10-26 |
| EQ-Bench Longform Creative Writing | 49.0% | EQ-Bench | 2026-11-11 |
Multimodal 54.2 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 82.5% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,235 | LMArena | 2026-11-09 |
Names matched to this model
gemini-3-1-flash-lite-preview