Gemini 3.5 Flash Lite High
| Released | 2026-07-21 |
|---|---|
| Price per 1M | $0.30 in · $2.50 out |
| Overall score | 52.8 · rank 231 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
| Configuration | High |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 52.8 | 231 | 19 |
| Overall: Coding | 53.2 | 215 | 12 |
| Overall: Reasoning | 51.4 | 245 | 11 |
| Overall: Agentic work | 53.9 | 221 | 11 |
| Overall: Frontend | 51.5 | 199 | 5 |
| Coding | 53.8 | 202 | 3 |
| Agents | 54.2 | 160 | 3 |
| Reasoning | 52.9 | 223 | 5 |
| Math | 49.9 | 179 | 4 |
| Knowledge | 50.4 | 127 | 2 |
| Frontend | 49.7 | 122 | 1 |
| Multimodal | 55.6 | 69 | 1 |
| Value vs price | +3.0 | 166 |
Evidence
Coding 53.8 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Vals run) | 75.0% | Vals AI | 2026-09-01 |
| LiveCodeBench (Vals run) | 79.0% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 54.2 ±22.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.1 (Vals run) | 50.2% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 7.3% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 59.1% | Vals AI | 2026-11-05 |
Reasoning 52.9 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 60.4% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 10.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 10.3% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 53.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 53.5% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 83.3% | Epoch AI | 2026-08-06 |
| GPQA Diamond (Vals run) | 83.8% | Vals AI | 2026-09-01 |
| Chess Puzzles | 16.0% | Epoch AI | 2026-10-13 |
Math 49.9 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 26.0% | Epoch AI | 2026-08-02 |
| FrontierMath Tier 4 | 0.0% | Epoch AI | 2026-08-02 |
| ProofBench | 13.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 71.1% | Epoch AI | 2026-08-06 |
Knowledge 50.4 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 85.8% | Vals AI | 2026-09-01 |
| Legal Research Bench | 13.9% | Vals AI | 2026-11-09 |
Frontend 49.7 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 37.2% | Vals AI | 2026-11-09 |
Multimodal 55.6 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 83.6% | Vals AI | 2026-09-01 |
Names matched to this model
gemini-3-5-flash-lite-high