Gemini 3.5 Flash
| Released | 2026-05-19 |
|---|---|
| Price per 1M | $1.50 in · $9.00 out |
| Overall score | 57.8 · rank 55 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 57.8 | 55 | 38 |
| Overall: Coding | 56.8 | 60 | 23 |
| Overall: Reasoning | 60.0 | 34 | 17 |
| Overall: Agentic work | 58.0 | 55 | 21 |
| Overall: Frontend | 54.3 | 63 | 9 |
| Coding | 56.9 | 57 | 5 |
| Agents | 57.3 | 58 | 7 |
| Reasoning | 62.3 | 24 | 9 |
| Math | 57.4 | 51 | 5 |
| Knowledge | 59.5 | 27 | 3 |
| Frontend | 51.8 | 67 | 2 |
| General | 54.2 | 73 | 5 |
| Multimodal | 60.9 | 15 | 2 |
| Value vs price | +6.4 | 59 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 56.6 ±3.2 | 9 |
| High | 58.5 ±0.8 | 29 |
| Low | 56.8 ±6.1 | 4 |
| Medium | 56.5 ±3.7 | 4 |
| Minimal | 52.0 ±5.1 | 5 |
Evidence
Coding 56.9 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 37.4% | Epoch AI | 2026-11-11 |
| SciCode | 53.9% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 87.6% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 79.3% | Epoch AI | 2026-06-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 78.8% | Vals AI | 2026-09-01 |
Agents 57.3 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 6.1% | Vals AI | 2026-11-09 |
| Terminal-Bench-Science | 5.7% | Vals AI | 2026-11-09 |
| APEX-Agents | 27.5% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.1 (Vals run) | 74.2% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 21.7% | Vals AI | 2026-11-09 |
| SkillsBench | 52.7% | Vals AI | 2026-10-29 |
| Vending-Bench 2 | $5,396 | Epoch AI | 2026-11-11 |
Reasoning 62.3 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 72.1% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 92.6% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 (ARC Prize verified) | 72.1% | ARC Prize | 2026-11-11 |
| CritPt | 13.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 92.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 92.5% | Epoch AI | 2026-11-11 |
| EnigmaEval | 25.4% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 92.8% | Epoch AI | 2026-05-22 |
| GPQA Diamond (Vals run) | 92.7% | Vals AI | 2026-09-01 |
| Chess Puzzles | 45.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 76.7% | SimpleBench | 2026-05-20 |
| SimpleBench | 76.7% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 32.0% | Epoch AI | 2026-07-27 |
Math 57.4 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 62.8% | Epoch AI | 2026-06-10 |
| FrontierMath Tier 4 | 26.8% | Epoch AI | 2026-06-10 |
| OTIS Mock AIME 2024-2025 | 95.6% | Epoch AI | 2026-05-25 |
| ProofBench v1.1 | 31.0% | Vals AI | 2026-11-09 |
| FrontierMath Tiers 1-3 (2025 set) | 39.0% | Epoch AI | 2026-05-22 |
| MathArena Final-Answer Competitions | 76.3% | MathArena | 2026-11-11 |
| ProofBench | 31.0% | Epoch AI | 2026-11-11 |
| FrontierMath Tier 4 (2025 set) | 14.6% | Epoch AI | 2026-05-25 |
Knowledge 59.5 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 66.2% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 89.5% | Vals AI | 2026-09-01 |
| Legal Research Bench | 30.8% | Vals AI | 2026-11-09 |
Frontend 51.8 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 48.7% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,500 | LMArena | 2026-11-09 |
General 54.2 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,400 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,077 | EQ-Bench | 2026-10-24 |
| LMArena Text | 1,478 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 22.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 71.8% | EQ-Bench | 2026-11-11 |
Multimodal 60.9 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 88.3% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,281 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 48.8% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 48.8% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 8.9% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 8.9% | ARC Prize | A stronger configuration result was used |
| Chess Puzzles | 42.0% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 27.0% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 36.1% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 88.9% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 86.4% | Epoch AI | A stronger configuration result was used |
| LMArena Text | 1,476 | LMArena | A stronger configuration result was used |
| LMArena Vision | 1,281 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,490 | LMArena | A stronger configuration result was used |
| Mystery Game Puzzles | 28.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 88.9% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 80.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-3-5-flash