GoogleGemini 2.0 Flash-Lite
Best configuration ranks #361 of 610 on the BenchLeader Index at 47.0 ±4.8. Last measured 2 Sept 2026.
- Blended price
- $0.131/M
- $0.075 in · $0.300 out
- Output speed
- –
- First answer
- –
- Context
- 1.0M
- Overall index47
- Reasoning51
- Coding47
- Human preference53
- Multimodal41
- Composite38
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| LMArena Hard Prompts | 1348#194 | LMArena |
| GPQA Diamond (AA)not in index | 54.2%#387 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.1%#457 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1343#228 | LMArena |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1353#176 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 1100#107 | LMArena |
| VISTA | 32.7%#48 | Scale AI SEAL |
| MMMU (validation) | 68.0%#24 | MMMU |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 7.4#397 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.0011 | – | – |
| Code edit | 6,000 / 1,500 | $0.0009 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.0057 | – | – |
| Structured extraction | 2,000 / 200 | $0.0002 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.