Gemini 3 Flash Preview
| Released | 2025-12-17 |
|---|---|
| Price per 1M | $0.50 in · $3.00 out |
| Overall score | 55.2 · rank 74 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 55.2 | 74 | 36 |
| Overall: Coding | 53.3 | 83 | 22 |
| Overall: Reasoning | 56.9 | 62 | 15 |
| Overall: Agentic work | 55.1 | 77 | 20 |
| Overall: Frontend | 49.5 | 92 | 10 |
| Coding | 53.9 | 88 | 4 |
| Agents | 54.9 | 75 | 9 |
| Reasoning | 58.0 | 64 | 7 |
| Math | 55.5 | 65 | 5 |
| Knowledge | 57.0 | 49 | 3 |
| Frontend | 45.6 | 89 | 2 |
| General | 55.5 | 62 | 2 |
| Multimodal | 59.6 | 20 | 4 |
| Value vs price | +7.1 | 51 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 54.9 ±1.5 | 20 |
| High | 55.4 ±1.4 | 22 |
| Low | 52.0 ±6.0 | 4 |
| Medium | 53.0 ±5.7 | 2 |
| Minimal | 52.3 ±4.0 | 7 |
Evidence
Coding 53.9 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GSO | 9.8% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 85.6% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 75.4% | Epoch AI | 2026-02-18 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 75.0% | Vals AI | 2026-09-01 |
Agents 54.9 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| tau2-bench Banking Knowledge | 27.3% | tau2-bench | 2026-03-02 |
| Terminal-Bench 2.0 | 64.3% | Epoch AI | 2025-12-17 |
| Tax Agent Bench | 11.8% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 53.9% | Vals AI | 2026-10-01 |
| tau2-bench Airline | 82.5% | tau2-bench | 2026-03-02 |
| DeepResearch Bench | 49.8% | Epoch AI | 2026-11-11 |
| BALROG | 48.1% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $3,635 | Epoch AI | 2026-11-11 |
| tau2-bench Telecom | 91.2% | tau2-bench | 2026-03-02 |
| tau2-bench Retail | 76.8% | tau2-bench | 2026-03-02 |
Reasoning 58.0 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 83.1% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 33.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 33.6% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 84.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 84.7% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 89.4% | Epoch AI | 2026-08-06 |
| GPQA Diamond (Vals run) | 87.9% | Vals AI | 2026-09-01 |
| Chess Puzzles | 40.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 61.1% | SimpleBench | 2025-12-19 |
| SimpleBench | 61.1% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 26.0% | Epoch AI | 2026-08-05 |
Math 55.5 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 51.2% | Epoch AI | 2026-06-11 |
| FrontierMath Tier 4 | 17.1% | Epoch AI | 2026-06-11 |
| ProofBench | 15.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 95.6% | Epoch AI | 2026-08-06 |
| MathArena Final-Answer Competitions | 67.6% | MathArena | 2026-11-11 |
| FrontierMath Tiers 1-3 (2025 set) | 35.6% | Epoch AI | 2025-12-17 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-12-17 |
Knowledge 57.0 ±6.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 66.8% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 88.6% | Vals AI | 2026-09-01 |
| Legal Research Bench | 18.3% | Vals AI | 2026-11-09 |
Frontend 45.6 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 20.2% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,440 | LMArena | 2026-11-09 |
General 55.5 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,473 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 55.7% | EQ-Bench | 2026-11-11 |
Multimodal 59.6 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,272 | LMArena | 2026-11-09 |
| MMMU-Pro (Vals run) | 87.6% | Vals AI | 2026-09-01 |
| VPCT | 72.6% | Epoch AI | 2026-11-11 |
| GeoBench | 88.0% | Epoch AI | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 (ARC Prize verified) | 21.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 29.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 57.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 3.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 1.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 12.8% | ARC Prize | A stronger configuration result was used |
| DeepResearch Bench | 47.9% | Epoch AI | A stronger configuration result was used |
| DeepResearch Bench | 49.0% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 83.2% | Epoch AI | A stronger configuration result was used |
| LMArena Text | 1,458 | LMArena | A stronger configuration result was used |
| LMArena Vision | 1,260 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,384 | LMArena | A stronger configuration result was used |
| Mystery Game Puzzles | 20.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 25.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 92.8% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 51.7% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 51.0% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-3-flash, gemini-3-flash-preview