AA-OmniscienceVerified
51.9%
AA-Omniscience Accuracy
Models / Google
Gemini 3.5 Flash
Gemini · Released 2026-05-19
Google's fastest frontier-tier model.
Default model for high-throughput, low-latency tool use: search agents, batch classification, real-time customer-facing apps. The cost-per-1M gap to Opus 4.8 is roughly 50× on input and 60× on output.
Composite56
Context1M
Input / 1M$0.30
Output / 1M$1.2
Knowledge cutoff2026-03-01
Output speed189 t/s
Statussolid
Family profile
Best published score in each covered benchmark family.
63/100 avg
- Knowledge
- 52
- Reasoning
- 74
- Math
- 39
- Coding
- 54
- Multimodal
- 84
- Long context
- 73
6 tested benchmark families
Editor's note
3.5 Flash is the model we recommend for high-volume tool use. The cost-per-1M gap to Opus 4.8 is roughly 50× on input and 60× on output — a meaningful line item for any team running agents at scale.Benchmark placements
Per-benchmark positions
Where Gemini 3.5 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 | #3/ 8 | 84 | Artificial Analysis — MMMU-Pro | 2026-09-01 |
| AA-Omniscience | Knowledge | #6/ 12 | 52 | Artificial Analysis — AA-Omniscience | 2026-09-01 |
| DeepSWE | Coding | #8/ 8 | 37 | DeepSWE leaderboard v1.1 | 2026-06-20 |
| FrontierMath | Math | #10/ 15 | 39 | Epoch AI FrontierMath Tiers 1-3 (v2) CSV | 2026-08-15 |
| AA output speed | Performance | #19/ 195 | Artificial Analysis | 2026-10-12 | |
| Humanity's Last Exam | Reasoning | #28/ 186 | 43 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #30/ 97 | 54 | Artificial Analysis | 2026-09-28 |
| AA-LCR | Long context | #101/ 184 | 73 | Artificial Analysis | 2026-09-28 |
| GPQA Diamond | Reasoning | #158/ 184 | 74 | Artificial Analysis GPQA Diamond evaluation | 2026-06-09 |
Family context
Strongest rows in each family
The three highest-scoring models with pages in each capability family. Where Gemini 3.5 Flash shows up, it's highlighted.
KnowledgeGemini 3.5 Flash · 52
- 167
- 265
- 361
ReasoningGemini 3.5 Flash · 74
- 196
- 295
- 395
MathGemini 3.5 Flash · 39
- 152
- 252
- 350
CodingGemini 3.5 Flash · 54
- 174
- 273
- 370
MultimodalGemini 3.5 Flash · 84
- 186
- 285
- 384
Long contextGemini 3.5 Flash · 73
- 189
- 286
- 385
Newest receipts
7 recentLast 120 days
Benchmark rows added to the public ledger for Gemini 3.5 Flash in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 189 t/s | Artificial Analysis | 10 |
| AA-LCR | Long context | 73.33% | Artificial Analysis | 24 |
| Humanity's Last Exam | Reasoning | 42.7% | Artificial Analysis | 24 |
| SciCode | Coding | 53.9% | Artificial Analysis | 24 |
| AA-Omniscience | Knowledge | 51.9% | Artificial Analysis — AA-Omniscience | 51 |
| MMMU-Pro | Multimodal | 84.3% | Artificial Analysis — MMMU-Pro | 51 |
| FrontierMath | Math | 38.97% | Epoch AI FrontierMath Tiers 1-3 (v2) CSV | 68 |
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 3.5 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 3.5 Flash. Scores link to the original source; gaps mean no public row exists yet.
9 of 13 catalog benchmarks have a sourced row for Gemini 3.5 Flash.
Knowledge
Reasoning
74.1%
GPQA Diamond
Humanity's Last ExamVerified
42.7%
HLE (AA run)
Math
FrontierMathVerified
38.97%
FrontierMath Tiers 1-3 (v2) best Epoch run
Coding
Multimodal
MMMU-ProVerified
84.3%
MMMU-Pro (AA run)
Long context
AA-LCRVerified
73.33%
AA-LCR (AA run)
Performance
AA output speedVerified
189 t/s
Median output tokens/s (1k prompt, default provider)
Sources
Where the numbers come from
- Gemini API pricing· checked 2026-06-01
- Gemini 3.5 family· checked 2026-06-01
- MCP Atlas leaderboard· checked 2026-06-01
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 3.5 Flash?
Gemini 3.5 Flash is a Google model: Google's fastest frontier-tier model.
What is Gemini 3.5 Flash for?
Default model for high-throughput, low-latency tool use: search agents, batch classification, real-time customer-facing apps. The cost-per-1M gap to Opus 4.8 is roughly 50× on input and 60× on output.
What does Gemini 3.5 Flash cost?
Gemini 3.5 Flash lists $0.30 input and $1.2 output per 1M tokens. Pricing last checked 2026-06-01.
How large is the Gemini 3.5 Flash context window?
Gemini 3.5 Flash publishes a 1M token context window.
What is the VerdictPal status of Gemini 3.5 Flash?
Gemini 3.5 Flash carries Solid 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.