Gemini 3.1 Pro Preview
| Released | 2026-02-19 |
|---|---|
| Price per 1M | $2.00 in · $12.00 out |
| Overall score | 57.5 · rank 56 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 57.5 | 56 | 50 |
| Overall: Coding | 55.1 | 70 | 33 |
| Overall: Reasoning | 61.3 | 24 | 21 |
| Overall: Agentic work | 57.0 | 61 | 31 |
| Overall: Frontend | 51.6 | 77 | 12 |
| Coding | 54.9 | 76 | 8 |
| Agents | 56.1 | 67 | 11 |
| Reasoning | 63.8 | 18 | 12 |
| Math | 57.5 | 46 | 5 |
| Knowledge | 62.3 | 14 | 4 |
| Frontend | 48.4 | 80 | 2 |
| General | 55.3 | 63 | 6 |
| Multimodal | 60.8 | 16 | 2 |
| Value vs price | +5.2 | 72 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 58.6 ±0.9 | 28 |
| High | 57.0 ±1.4 | 25 |
| Low | 53.0 ±7.1 | 2 |
| Medium | 59.6 ±12.0 | 1 |
Evidence
Coding 54.9 ±2.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 11.7% | Epoch AI | 2026-11-11 |
| MirrorCode | 8.9% | Epoch AI | 2026-08-10 |
| GSO | 22.6% | Epoch AI | 2026-11-11 |
| IOI | 51.8% | Vals AI | 2026-10-29 |
| SWE-bench Verified (Vals run) | 78.8% | Vals AI | 2026-09-01 |
| SciCode | 58.7% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 88.5% | Vals AI | 2026-09-01 |
| ProgramBench | 0.0% | Vals AI | 2026-11-09 |
Agents 56.1 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 2.5% | Vals AI | 2026-11-09 |
| SRE Bench | 0.0% | Vals AI | 2026-11-05 |
| Terminal-Bench-Science | 1.4% | Vals AI | 2026-11-09 |
| APEX-Agents | 35.1% | Epoch AI | 2026-11-11 |
| METR 50% Time Horizon | $384 | METR | 2026-11-11 |
| tau2-bench Banking Knowledge | 26.0% | tau2-bench | 2026-05-05 |
| Terminal-Bench 2.0 | 80.2% | Epoch AI | 2026-02-19 |
| Tax Agent Bench | 9.3% | Vals AI | 2026-11-09 |
| METR task suite | 77.0% | Epoch AI | 2026-11-11 |
| Terminal-Bench 2.1 (Vals run) | 70.8% | Vals AI | 2026-10-01 |
| DeepResearch Bench | 47.8% | Epoch AI | 2026-11-11 |
| BALROG | 57.0% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $911 | Epoch AI | 2026-11-11 |
Reasoning 63.8 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 77.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 77.1% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 97.4% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 20.7% | Vals AI | 2026-11-09 |
| CritPt | 17.7% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 98.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 98.0% | Epoch AI | 2026-11-11 |
| EnigmaEval | 36.8% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 94.4% | Epoch AI | 2026-08-06 |
| GPQA Diamond (Vals run) | 95.5% | Vals AI | 2026-09-01 |
| BioMysteryBench | 60.0% | Vals AI | 2026-11-09 |
| ARC-AGI-3 | 0.4% | ARC Prize | 2026-11-11 |
| Chess Puzzles | 51.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 79.6% | SimpleBench | 2026-02-17 |
| SimpleBench | 79.6% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 34.0% | Epoch AI | 2026-07-27 |
Math 57.5 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 59.7% | Epoch AI | 2026-06-11 |
| FrontierMath Tier 4 | 26.8% | Epoch AI | 2026-06-11 |
| OTIS Mock AIME 2024-2025 | 95.6% | Epoch AI | 2026-02-20 |
| ProofBench v1.1 | 26.0% | Vals AI | 2026-11-09 |
| FrontierMath Tiers 1-3 (2025 set) | 36.9% | Epoch AI | 2026-02-19 |
| MathArena Final-Answer Competitions | 86.5% | MathArena | 2026-11-11 |
| ProofBench | 26.0% | Epoch AI | 2026-11-11 |
| FrontierMath Tier 4 (2025 set) | 16.7% | Epoch AI | 2026-02-19 |
Knowledge 62.3 ±4.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 73.5% | Epoch AI | 2026-08-10 |
| Humanity's Last Exam | 46.4% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 91.0% | Vals AI | 2026-09-01 |
| Legal Research Bench | 20.7% | Vals AI | 2026-11-09 |
Frontend 48.4 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 32.0% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,446 | LMArena | 2026-11-09 |
General 55.3 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,482 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,132 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,491 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,487 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 19.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 68.2% | EQ-Bench | 2026-11-11 |
Multimodal 60.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 88.2% | 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 |
|---|---|---|---|
| DeepResearch Bench | 44.5% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 94.1% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 32.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 29.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 95.6% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 78.4% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 78.4% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 74.8% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 61.4% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-3-1-pro, gemini-3-1-pro-preview, gemini-pro, gemini-pro-latest