Agnes 3.0 Flash vs Gemini 3.7 Flash
Agnes 3.0 Flash 
Gemini 3.7 Flash Verdict
- Gemini 3.7 Flash (medium) leads on quality: 64.7 vs 62.3.
- Agnes 3.0 Flash is stronger in agents & tools, reasoning.
- Gemini 3.7 Flash (medium) is stronger in composite, knowledge, long context, coding, multimodal.
- Agnes 3.0 Flash is 20× cheaper ($0.075 vs $1.50 per 1M blended).
| Metric | Agnes 3.0 Flash | Gemini 3.7 Flash (medium) |
|---|---|---|
| BenchLeader Index | 62.3 | 64.7 |
| Agents & tools score | 76.8 | 64.1 |
| Composite score | 74.0 | 79.2 |
| Knowledge score | 59.1 | 75.5 |
| Long context score | 67.0 | 68.0 |
| Reasoning score | 71.1 | 62.1 |
| Coding score | – | 68.5 |
| Multimodal score | – | 69.4 |
| Blended price $/M | $0.075 | $1.50 |
| Output speed | – | 276 tok/s |
| Time to first answer | – | 5.4 s |
| Context window | 1M | 1.0M |
| SciCode | – | 57.9% |
| AA Intelligence Index | 35.5 | 39.6 |
| AA-LCR | 81.0% | 83.0% |
| MMMU-Pro | – | 84.7% |
| AA-Omniscience | -10.6 | 23.7 |
| GPQA Diamond (AA) | 92.4% | 92.1% |
| Humanity's Last Exam (AA) | 38.5% | 39.0% |
| SciCode (AA) | 51.6% | 59.8% |
| ARC-AGI-1 | – | 91.2% |
| ARC-AGI-2 | – | 63.8% |
| CritPt | 15.1% | 9.4% |
| GDPval (AA) | 53.7% | 45.3% |
| τ²-Bench Banking (AA) | 47.6% | 35.5% |
| DeepSWE | – | 65.5% |
| CursorBench | – | 59.0% |
| GDP.pdf | – | 21.8% |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
Agnes 3.0 Flash vs Gemini 3.7 Flash: questions
- Is Agnes 3.0 Flash better than Gemini 3.7 Flash?
- Gemini 3.7 Flash (medium) leads on quality: 64.7 vs 62.3. The BenchLeader Index combines every independent quality benchmark; Gemini 3.7 Flash (medium) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Is Agnes 3.0 Flash better than Gemini 3.7 Flash for agentic tasks?
- Agnes 3.0 Flash scores higher in agentic tasks (77 vs 64 on the category index, where 50 is average).
- Which is cheaper, Agnes 3.0 Flash or Gemini 3.7 Flash?
- Agnes 3.0 Flash is cheaper: $0.075 against $1.50 per million tokens, blended at three input tokens per output token.
- Which has the larger context window?
- Gemini 3.7 Flash accepts more context: 1.0M against 1M tokens.