Gemini 3.6 Flash
| Released | 2026-07-21 |
|---|---|
| Price per 1M | $0.75 in · $3.75 out |
| Overall score | 58.2 · rank 51 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.2 | 51 | 35 |
| Overall: Coding | 57.6 | 53 | 23 |
| Overall: Reasoning | 59.0 | 46 | 16 |
| Overall: Agentic work | 58.6 | 47 | 21 |
| Overall: Frontend | 56.2 | 54 | 12 |
| Coding | 57.3 | 54 | 8 |
| Agents | 58.5 | 46 | 5 |
| Reasoning | 60.9 | 37 | 8 |
| Math | 56.9 | 54 | 5 |
| Knowledge | 58.5 | 38 | 3 |
| Frontend | 54.9 | 56 | 2 |
| General | 57.4 | 43 | 2 |
| Multimodal | 60.9 | 14 | 2 |
| Value vs price | +9.3 | 33 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 57.7 ±3.3 | 4 |
| High | 58.5 ±0.9 | 30 |
| Low | 54.5 ±5.1 | 6 |
| Medium | 58.2 ±4.0 | 3 |
| Minimal | 50.7 ±5.2 | 6 |
Evidence
Coding 57.3 ±1.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 46.7% | Epoch AI | 2026-11-11 |
| FrontierCode | 34.4% | Epoch AI | 2026-11-11 |
| MirrorCode | 23.3% | Epoch AI | 2026-10-21 |
| IOI | 35.1% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 79.6% | Vals AI | 2026-09-01 |
| SciCode | 53.4% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 88.1% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 58.5 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| APEX-Agents | 46.9% | Epoch AI | 2026-11-11 |
| Terminal-Bench-Science | 4.3% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 73.8% | Vals AI | 2026-10-01 |
| Tax Agent Bench | 18.0% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 45.4% | Vals AI | 2026-11-05 |
Reasoning 60.9 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 89.0% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 60.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 60.4% | ARC Prize | 2026-11-11 |
| CritPt | 10.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 91.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 91.2% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 94.1% | Epoch AI | 2026-08-02 |
| GPQA Diamond (Vals run) | 93.4% | Vals AI | 2026-09-01 |
| BioMysteryBench | 58.5% | Vals AI | 2026-11-09 |
| Chess Puzzles | 42.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 30.0% | Epoch AI | 2026-08-05 |
Math 56.9 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 59.0% | Epoch AI | 2026-08-02 |
| FrontierMath Tier 4 | 22.0% | Epoch AI | 2026-08-02 |
| ProofBench | 36.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 94.2% | Epoch AI | 2026-08-02 |
| MathArena Final-Answer Competitions | 70.8% | MathArena | 2026-11-11 |
Knowledge 58.5 ±4.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 66.2% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 89.3% | Vals AI | 2026-09-01 |
| Legal Research Bench | 25.0% | Vals AI | 2026-11-09 |
Frontend 54.9 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 64.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,538 | LMArena | 2026-11-09 |
General 57.4 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 1,602 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,483 | LMArena | 2026-11-09 |
Multimodal 60.9 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 88.4% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,280 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 34.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 76.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 83.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 34.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 76.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 83.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 2.6% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 30.4% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 50.4% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 2.6% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 30.4% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 50.4% | ARC Prize | A stronger configuration result was used |
| Chess Puzzles | 29.0% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 40.0% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 85.9% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 86.4% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 25.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 23.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 80.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 82.2% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-3-6-flash