GPQA DiamondVerified
94.5%
GPQA Diamond (AA run)
Models / Google
Gemini 3.7 Flash
Gemini 3.7 · Released 2026-08-13
Google's August 2026 Flash workhorse, superseded as the current Flash by Gemini 3.8 Flash on 2 Sep 2026. Introductory API price still $0.75 / $3.75 per 1M tokens through 31 Dec 2026.
Previous Google Flash when 3.8 Flash is too verbose or you want the faster 305 t/s high-effort endpoint. Prefer sourced ledger rows; live AA v4.3 scores are not comparable to the August v4.1 snapshot.
Composite74
Context1M
Input / 1M$0.75
Output / 1M$3.8
Knowledge cutoffunpublished
Output speed314 t/s
Statusflagship
Family profile
Best published score in each covered benchmark family.
81/100 avg
- Reasoning
- 95
- Coding
- 57
- Agentic
- 86
- Multimodal
- 86
- Long context
- 82
5 tested benchmark families
Editor's note
Editorial depth still needs a desk pass.Benchmark placements
Per-benchmark positions
Where Gemini 3.7 Flash places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| MMMU-Pro | Multimodal | #1/ 8 | 86 | Artificial Analysis — MMMU-Pro | 2026-09-01 |
| AA output speed | Performance | #4/ 195 | Artificial Analysis | 2026-10-12 | |
| GPQA Diamond | Reasoning | #5/ 184 | 95 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #13/ 186 | 48 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #13/ 97 | 57 | Artificial Analysis | 2026-09-28 |
| Terminal-Bench | Agentic | #13/ 167 | 86 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #25/ 184 | 82 | Artificial Analysis | 2026-09-28 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Gemini 3.7 Flash shows up, it's highlighted.
ReasoningGemini 3.7 Flash · 95
- 196
- 295
- 395
Math
- 152
- 252
- 350
CodingGemini 3.7 Flash · 57
- 174
- 273
- 370
AgenticGemini 3.7 Flash · 86
- 191
- 289
- 389
MultimodalGemini 3.7 Flash · 86
- 186
- 285
- 384
Long contextGemini 3.7 Flash · 82
- 189
- 286
- 385
Newest receipts
7 recentLast 120 days
Benchmark rows added to the public ledger for Gemini 3.7 Flash in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 314 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 81.67% | Artificial Analysis | 24 |
| GPQA Diamond | Reasoning | 94.5% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 47.9% | Artificial Analysis | 24 |
| SciCode | Coding | 57.2% | Artificial Analysis | 24 |
| Terminal-Bench | Agentic | 85.77% | Artificial Analysis | 24 |
| MMMU-Pro | Multimodal | 85.5% | Artificial Analysis — MMMU-Pro | 51 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where Gemini 3.7 Flash sits on the scatter
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
AnthropicOpenAIGoogleAlibabaMetaZhipuxAIDeepSeekMiniMaxXiaomiMoonshotOtherMeituanMistralNVIDIACohere
Full benchmark ledger
Every catalog benchmark for Gemini 3.7 Flash. Scores link to the original source; gaps mean no public row exists yet.
7 of 13 catalog benchmarks have a sourced row for Gemini 3.7 Flash.
Reasoning
Humanity's Last ExamVerified
47.9%
HLE (AA run)
Coding
SciCodeVerified
57.2%
SciCode (AA run)
Agentic
Terminal-BenchVerified
85.77%
Terminal-Bench v2.1 (AA run)
Multimodal
MMMU-ProVerified
85.5%
MMMU-Pro (AA run)
Long context
AA-LCRVerified
81.67%
AA-LCR (AA run)
Performance
AA output speedVerified
314 t/s
Median output tokens/s (1k prompt, default provider)
Changelog
Version history
- Gemini 3.8 Flash remains the current Flash.
- Gemini 3.8 Flash is now the current Flash; 3.7 stays listed for the faster 305 t/s endpoint.
- Gemini 3.7 Flash generally available. Google reports gains over 3.6 Flash on FrontierCode 1.1, DeepSWE v1.1, WebDev Arena, and GDP.pdf — vendor-claimed, not ledger rows.
Sources
Where the numbers come from
- Google Gemini 3.7 Flash announcement· checked 2026-08-13
- DeepMind Gemini 3.7 Flash model card· checked 2026-08-13
- Artificial Analysis Gemini 3.7 Flash· checked 2026-08-13
- Gemini API release notes· checked 2026-09-05
Questions this model page answers
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
What is Gemini 3.7 Flash?
Gemini 3.7 Flash is a Google model: Google's August 2026 Flash workhorse, superseded as the current Flash by Gemini 3.8 Flash on 2 Sep 2026. Introductory API price still $0.75 / $3.75 per 1M tokens through 31 Dec 2026.
What is Gemini 3.7 Flash for?
Previous Google Flash when 3.8 Flash is too verbose or you want the faster 305 t/s high-effort endpoint. Prefer sourced ledger rows; live AA v4.3 scores are not comparable to the August v4.1 snapshot.
What does Gemini 3.7 Flash cost?
Gemini 3.7 Flash lists $0.75 input and $3.8 output per 1M tokens. Pricing last checked 2026-09-05.
How large is the Gemini 3.7 Flash context window?
Gemini 3.7 Flash publishes a 1M token context window.
What is the VerdictPal status of Gemini 3.7 Flash?
Gemini 3.7 Flash carries Flagship status on the model atlas.
The Pack · Editorial newsletter
Know when the rules move.
One short email when a university changes its AI rule for theses, or a research tool changes its pricing or privacy terms. No tracking, no third-party analytics. Unsubscribe in one click.