Gemini 2.5 Flash
| Released | 2025-06-17 |
|---|---|
| Price per 1M | $0.30 in · $2.50 out |
| Overall score | 47.3 · rank 132 |
| Context window | 1,048,576 tokens |
| Provider | |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 47.3 | 132 | 11 |
| Overall: Coding | 46.0 | 147 | 7 |
| Overall: Reasoning | 47.0 | 140 | 5 |
| Overall: Agentic work | 45.8 | 147 | 7 |
| Overall: Frontend | 50.5 | 86 | 1 |
| Agents | 45.6 | 132 | 4 |
| Reasoning | 46.7 | 140 | 3 |
| Math | 47.5 | 134 | 2 |
| General | 49.8 | 111 | 1 |
| Multimodal | 50.5 | 73 | 1 |
| Value vs price | +0.0 | 120 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 46.9 ±3.0 | 11 |
| Thinking | 47.0 ±9.4 | 1 |
Evidence
Agents 45.6 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 17.1% | Epoch AI | 2025-06-17 |
| BFCL v4 | 56.2% | BFCL | 2026-04-12 |
| BALROG | 33.5% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $549 | Epoch AI | 2026-11-11 |
Reasoning 46.7 ±4.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 1.1% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 56.8% | Kagi | 2026-11-11 |
| SimpleBench | 41.2% | SimpleBench | 2025-10-22 |
| SimpleBench | 41.2% | Epoch AI | 2026-11-11 |
Math 47.5 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 4.8% | Epoch AI | 2025-12-18 |
| FrontierMath Tier 4 (2025 set) | 4.2% | Epoch AI | 2025-12-18 |
General 49.8 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,409 | LMArena | 2026-11-09 |
Multimodal 50.5 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,215 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| BFCL v4 | 50.9% | BFCL | A stronger configuration result was used |
| Kagi Reasoning Benchmark | 44.1% | Kagi | A stronger configuration result was used |
| Terminal-Bench 2.0 | 16.9% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 16.4% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 15.5% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gemini-2-5-flash