Gemini 2.5 Pro
| Released | 2025-06-17 |
|---|---|
| Price per 1M | $1.25 in · $10.00 out |
| Overall score | 49.0 · rank 122 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 49.0 | 122 | 20 |
| Overall: Coding | 45.4 | 149 | 15 |
| Overall: Reasoning | 50.8 | 108 | 9 |
| Overall: Agentic work | 48.8 | 122 | 13 |
| Overall: Frontend | 36.1 | 195 | 6 |
| Coding | 48.3 | 129 | 3 |
| Agents | 48.4 | 116 | 4 |
| Reasoning | 51.2 | 107 | 6 |
| Math | 50.3 | 109 | 3 |
| Frontend | 26.8 | 133 | 2 |
| General | 54.9 | 68 | 1 |
| Multimodal | 55.1 | 48 | 1 |
| Value vs price | −2.5 | 146 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 49.2 ±1.5 | 17 |
| High | 49.6 ±6.1 | 1 |
| Thinking | 49.6 ±5.7 | 2 |
Evidence
Coding 48.3 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GSO | 3.9% | Epoch AI | 2026-11-11 |
| SciCode | 46.3% | Epoch AI | 2026-11-11 |
| SWE-bench Verified (Epoch run) | 57.6% | Epoch AI | 2026-02-13 |
| SWE-bench Verified (Vals run) | 54.4% | Vals AI | 2026-09-01 |
Agents 48.4 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 32.6% | Epoch AI | 2025-06-17 |
| tau2-bench Banking Knowledge | 13.7% | tau2-bench | 2026-05-05 |
| DeepResearch Bench | 41.5% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $574 | Epoch AI | 2026-11-11 |
Reasoning 51.2 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 4.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 4.9% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 85.3% | Epoch AI | 2025-11-16 |
| CritPt | 2.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 41.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 41.0% | Epoch AI | 2026-11-11 |
| SimpleBench | 62.4% | SimpleBench | 2026-11-11 |
| Kagi Reasoning Benchmark | 70.3% | Kagi | 2026-11-11 |
Math 50.3 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.7% | Epoch AI | 2025-11-16 |
| FrontierMath Tier 4 | 0.0% | Epoch AI | 2026-06-11 |
| FrontierMath Tiers 1-3 | 24.6% | Epoch AI | 2026-06-11 |
| FrontierMath Tiers 1-3 (2025 set) | 14.1% | Epoch AI | 2025-11-24 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-07-03 |
Frontend 26.8 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 0.4% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,227 | LMArena | 2026-11-09 |
General 54.9 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,446 | LMArena | 2026-11-09 |
Multimodal 55.1 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,247 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Terminal-Bench 2.0 | 26.1% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 19.6% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 16.4% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-2-5-pro