GoogleGemma 3n E4B
Best configuration ranks #575 of 610 on the BenchLeader Index at 36.6 ±6.8. Last measured 2 Sept 2026. Released 3 Jun 2025.
- Blended price
- $0.075/M
- $0.060 in · $0.120 out
- Output speed
- –
- First answer
- –
- Context
- 128k
- Overall index37
- Reasoning39
- Coding43
- Agents & tools36
- Knowledge26
- Instruction following32
- Human preference48
- Multimodal10
- Long context25
- Composite36
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 | 1312#229 | LMArena |
| GPQA Diamond (AA)not in index | 29.6%#492 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.8%#392 | Artificial Analysis |
| Kagi LLM Benchmark | 31.5%#122 | Kagi LLM Benchmark |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1307#249 | LMArena |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 2.3%#304 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 5.0%#372 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -81.3#462 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 27.9%#357 | Artificial Analysis |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1317#217 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| MMMU-Pro | 26.2%#242 | Artificial Analysis |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 0.0%#419 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 5.8#471 | 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 | $0.0008 | – | – |
| Code edit | 6,000 / 1,500 | $0.0005 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.0041 | – | – |
| Structured extraction | 2,000 / 200 | $0.0001 | – | – |
See also
Data as of 9 Sept 2026. Compare with another model.