Gemini 1.5 Pro (Sept 2024)
| Released | 2024-09-24 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 39.2 · rank 198 |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 39.2 | 198 | 12 |
| Overall: Coding | 37.7 | 198 | 5 |
| Overall: Reasoning | 40.1 | 191 | 7 |
| Overall: Agentic work | 39.2 | 194 | 5 |
| Overall: Frontend | 37.8 | 184 | 3 |
| Coding | 36.3 | 187 | 1 |
| Agents | 39.7 | 158 | 1 |
| Reasoning | 41.7 | 176 | 3 |
| Math | 39.5 | 162 | 2 |
| Knowledge | 37.4 | 148 | 2 |
| General | 41.6 | 157 | 1 |
| Multimodal | 42.6 | 99 | 2 |
Evidence
Coding 36.3 ±5.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveCodeBench (Vals run) | 41.7% | Vals AI | 2026-09-01 |
Agents 39.7 ±7.1
Reasoning 41.7 ±3.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 0.8% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 57.2% | Epoch AI | 2025-01-27 |
| GPQA Diamond (Vals run) | 58.3% | Vals AI | 2026-09-01 |
| SimpleBench | 27.1% | SimpleBench | 2026-11-11 |
| SimpleBench | 27.1% | Epoch AI | 2026-11-11 |
Math 39.5 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 70.4% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 23.1% | Epoch AI | 2025-02-25 |
Knowledge 37.4 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 4.6% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 75.3% | Vals AI | 2026-09-01 |
General 41.6 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,351 | LMArena | 2026-11-09 |
Multimodal 42.6 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 65.5% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,180 | LMArena | 2026-11-09 |
Names matched to this model
gemini-1-5-pro-002, gemini-1-5-pro-sept-2024