Data as of November 11, 2026 · How the score is built
Released Aug 13, 20261M contextGoogle DeepMind Gemini 3.7 Flash model card
Gemini 3.7 Flash
Decision readingGemini 3.7 Flash scores 66.2 out of 100 and ranks #25 of 214. This profile shows 37 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #14. API pricing is $0.75 input and $3.75 output per million tokens, with cached input at $0.075.
Released Aug 13, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
66.2/100
field median 51.2#25 of 214 ranked models
Public
#25of 214
Verified #18 of 79
Price
$0.75input / $3.75 output
input median $0.60cached $0.075 · blended $2.25
Speed
285tok/s
field median 92 tok/sFirst token 8.52 s
Context
1Mtokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Multimodal & Grounded ranks #14. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
37 published rows leave some tracked benchmark slots empty. Reasoning is its lowest eligible category at #25.
Source-linked · 37 displayable benchmark rows
Is Gemini 3.7 Flash right for your job?
Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.
Gemini 3.7 Flash has a newer version, Gemini 3.8 Flash. Where Gemini 3.8 Flash ranks by benchmark score:
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #24 of 132Percentile 82ndWeight 22%9 benchmarksVerified | 60.9 | 9 benchmarks | Verified | |||
| CodingRank #25 of 158Percentile 85thWeight 20%6 benchmarksVerified | 57.7 | 6 benchmarks | Verified | |||
| ReasoningRank #25 of 158Percentile 85thWeight 17%3 benchmarksVerified | 62.9 | 3 benchmarks | Verified | |||
| MultimodalRank #14 of 67Percentile 80thWeight 12%4 benchmarksVerified | 70.1 | 4 benchmarks | Verified | |||
| KnowledgeRank #15 of 179Percentile 92ndWeight 12%6 benchmarksVerified | 70.2 | 6 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathRank Not rankedWeight 5%2 benchmarksVerified | 70.2 | 2 benchmarks | Verified |
37 of 894 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic9/9 verified
- Coding6/6 verified
- Reasoning3/3 verified
- Multimodal4/4 verified
- Knowledge6/6 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math2/2 verified
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Gemini 3.7 Flash category percentile values
- Agentic82nd percentile
- Coding85th percentile
- Reasoning85th percentile
- Multimodal80th percentile
- Knowledge92nd percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#24/132
- Coding#25/158
- Reasoning#25/158
- Multimodal#14/67
- Knowledge#15/179
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Every result says who ran the test. For this model, Google ran 16 of 37. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.
Coding6 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| DeepSWE | 65.3% | Best verified: Muse Wonder Full · 79.0% | Gap13.7 behind | Reported by Google | Counts15% ref. weight |
| FrontierSWE v2 | 20.3% | Best verified: Claude Fable 5.2 · 69.9% | Gap49.6 behind | Run by FrontierSWE v2 | Counts8% ref. weight |
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | 88.7% | Best verified: Claude Fable 5.1 · 90.5% | Gap1.8 behind | Independent run: Vals AI | Counts8% ref. weight |
| FrontierCode 1.1 Main | 43.6% | Best verified: Claude Opus 5.5 · 54.4% | Gap10.8 behind | Reported by Google | Counts4% ref. weight |
| Terminal-Bench 2.1 | 85.8% | Best verified: SWE-2 · 92.8% | Gap7 behind | Reported by Google | CountsScored in Agentic |
| SWE-bench (Vals)SWE-bench, Vals AI run | 80.8% | Best verified: Claude Opus 5 · 97.0% | Gap16.2 behind | Independent run: Vals AI | Shown only |
Agentic9 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | 85.8% | Best verified: SWE-2 · 92.8% | Gap7 behind | Reported by Google | Counts8% ref. weight |
| AutomationBench | 30.4% | Best verified: MiniMax M3.1 Flash · 62.2% | Gap31.8 behind | Reported by Google | Counts6% ref. weight |
| Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run | 77.5% | Best verified: GPT-6 Astra · 87.3% | Gap9.8 behind | Independent run: Vals AI | Counts4% ref. weight |
| Terminal-Bench 3.0 | 14.9% | Best verified: Claude Opus 5 · 42.7% | Gap27.8 behind | Reported by Google | Counts3% ref. weight |
| Agents' Last Exam | 26.3% | Best verified: GPT-6.1 Terra · 60.0% | Gap33.7 behind | Reported by Google | Counts3% ref. weight |
| Terminal-Bench 4.1 | 12.40% | Best verified: Claude Opus 5.5 · 65.80% | Gap53.4 behind | Run by Terminal-Bench 4.1 | Shown only |
| OSWorld 2.0 | 47.9% | Best verified: Kimi K3.1 Pro · 79.6% | Gap31.7 behind | Reported by Google | Shown only |
| ApprenticeBenchApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | 16% | Best verified: Claude Fable 5.1 · 72% | Gap56 behind | Run by ApprenticeBench | Shown only |
| MazeBenchMazeBench: visual spatial reasoning in a 3D open world | 1% | Best verified: GPT-6 Astra · 23% | Gap22 behind | Run by MazeBench | Shown only |
Reasoning3 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | 84.6% | Best verified: GPT-6 Astra · 95% | Gap10.4 behind | Run by ARC-AGI-2 | Counts15% ref. weight |
| MRCR v2 64K-128KOpenAI MRCR v2 8-needle 64K-128K | 97% | Best verified: Gemini 3.7 Flash · 97% | GapHighest listed | Reported by Google | Shown only |
| ARC-AGI-1ARC-AGI-1 Semi-Private Evaluation | 95.50% | Best verified: Claude Fable 5 · 98.50% | Gap3 behind | Run by ARC-AGI-1 | Shown only |
Multimodal4 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| CharXivCharXiv Reasoning | 88.7% | Best verified: Qwen3.8 Max · 93.5% | Gap4.8 behind | Reported by Google | Counts17% ref. weight |
| ParseBenchParseBench: document parsing for AI agents (LlamaIndex leaderboard) | 70.37% | Best verified: Claude Opus 5.5 · 78.80% | Gap8.4 behind | Run by ParseBench | Counts7% ref. weight |
| CharXiv w/o toolsCharXiv Reasoning without tools | 84.5% | Best verified: Kimi K3.1 Pro · 89% | Gap4.5 behind | Reported by Google | Counts7% ref. weight |
| LVBench | 85.4% | Best verified: Gemini 4 Argon · 91.7% | Gap6.3 behind | Reported by Google | Shown only |
Knowledge6 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | 90.1% | Best verified: Claude Fable 5.1 · 92.4% | Gap2.3 behind | Independent run: Vals AI | Counts6% ref. weight |
| GPQA Diamond (Vals)GPQA Diamond, Vals AI run | 93.9% | Best verified: Gemini 3.1 Pro · 95.5% | Gap1.6 behind | Independent run: Vals AI | Counts2% ref. weight |
| HLE-Verified | 53.6% | Best verified: Gemini 3.8 Flash · 54.9% | Gap1.3 behind | Reported by Google | Shown only |
| LABBench2LABBench2: An Improved Benchmark for AI Systems Performing Biology Research | 82.1% | Best verified: Gemini 4 Argon · 88.8% | Gap6.7 behind | Reported by Google | Shown only |
| BioMysteryBench (human-solvable)BioMysteryBench Human Solvable | 87.1% | Best verified: Claude Opus 5 · 90.1% | Gap3 behind | Reported by Google | Shown only |
| BioMysteryBench (human-difficult)BioMysteryBench Human Difficult | 43.5% | Best verified: Gemini 3.8 Flash · 56.5% | Gap13 behind | Reported by Google | Shown only |
Math2 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | 71.579% | Best verified: Claude Fable 5.2 · 95.088% | Gap23.5 behind | Run by FrontierMath v2 (Tiers 1-3) | CountsWeighted 30% |
| FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4 | 36.585% | Best verified: Claude Fable 5.2 · 100.000% | Gap63.4 behind | Run by FrontierMath v2 (Tier 4) | CountsWeighted 10% |
External signals7 rows
| Benchmark | Score | Versus best verified row | Gap | Who ran it | Use in ranking |
|---|---|---|---|---|---|
| NYT ConnectionsNYT Connections LLM Benchmark (extended version) | 94.0% | Best verified: Gemini 4 Argon · 98.6% | Gap4.6 behind | Run by NYT Connections | Shown only |
| Code2Video | 1477 | Best verified: Claude Opus 5.5 · 1585 | Gap108 behind | Run by Code2Video | Shown only |
| BabaIsBenchBabaIsBench (Baba Is You intro levels, pass@1) | 100% | Best verified: Claude Opus 5 · 100% | GapBest verified | Run by BabaIsBench | Shown only |
| Chess PuzzlesChess Puzzles (Epoch AI) | 66.0% | Best verified: Claude Fable 5.2 · 79.0% | Gap13 behind | Run by Chess Puzzles | Shown only |
| Mystery Game PuzzlesMystery Game Puzzles (Epoch AI) | 37.0% | Best verified: Claude Fable 5.2 · 90.0% | Gap53 behind | Run by Mystery Game Puzzles | Shown only |
| Furniture AssemblyFurniture Assembly Benchmark (Epoch AI) | 26.7% | Best verified: Claude Fable 5.2 · 90.0% | Gap63.3 behind | Run by Furniture Assembly | Shown only |
| MirrorCodeMirrorCode (Epoch AI and METR) | 41.1% | Best verified: Claude Opus 5.5 · 78.9% | Gap37.8 behind | Run by MirrorCode | Shown only |
Outlined bars are lab-reported. Filled bars are benchmark-run or independent.
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
Gemini 3.7 Flash · 66.2 score · $2.25 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gemini-3.7-flashGoogle Gemini 3.7 Flash API documentation
- Context window
- 1MGoogle Gemini 3.7 Flash API documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, image, video, audio, pdfGoogle Gemini 3.7 Flash API documentation
- Output modalities
- textGoogle Gemini 3.7 Flash API documentation
- Parameters
- Not disclosed by the provider
- Availability
- Gemini API · Google AI Studio · Gemini App - Spark · Gemini Enterprise App · Gemini Enterprise Agent Platform · Google AntigravityGoogle DeepMind Gemini 3.7 Flash model card
- Cloud regions
- Not tracked yet
- Lifecycle
- activeGoogle Gemini 3.7 Flash API documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.075 per million cached input tokensGoogle Gemini API pricing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Gemini 3.7 Flash ranks #25 of 214 on the public leaderboard with a score of 66.21/100. Its source-verified position is #18 of 79.
Gemini 3.7 Flash is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Generally available as the stable `gemini-3.7-flash` model through the Gemini API and Google AI Studio. Google also distributes it through Gemini App - Spark, Gemini Enterprise App, Gemini Enterprise Agent Platform, and Google Antigravity.
Its explicit predecessor is Gemini 3.6 Flash. 37 of 894 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #14, while its lowest eligible position is Reasoning at #25. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Last updated November 11, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Gemini 3.7 Flash by API
2 hosts publish a per-token price for it. DeepInfra has the lowest output rate, $3.75 per million tokens. Prices read from each host’s own pages on November 11, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| DeepInfra | $0.75 | $3.75 | — | 1M |
| OpenRouter | $0.75 | $3.75 | $0.075 | 1.05M |
Questions
How does Gemini 3.7 Flash perform overall in AI benchmarks?
Gemini 3.7 Flash ranks #25 out of 214 models on the public BenchAlign leaderboard, with a score of 66.21/100. Its evidence status is Supported, and this profile shows 37 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Gemini 3.7 Flash good for knowledge and understanding?
Gemini 3.7 Flash ranks #15 out of 179 eligible models for knowledge and understanding, with a public category score of 70.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Gemini 3.7 Flash good for coding and programming?
Gemini 3.7 Flash ranks #25 out of 158 eligible models for coding and programming, with a public category score of 57.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Gemini 3.7 Flash good for mathematics?
Gemini 3.7 Flash has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Gemini 3.7 Flash good for reasoning and logic?
Gemini 3.7 Flash ranks #25 out of 158 eligible models for reasoning and logic, with a public category score of 62.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Gemini 3.7 Flash good for agentic tool use and computer tasks?
Gemini 3.7 Flash ranks #24 out of 132 eligible models for agentic tool use and computer tasks, with a public category score of 60.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Gemini 3.7 Flash good for multimodal and grounded tasks?
Gemini 3.7 Flash ranks #14 out of 67 eligible models for multimodal and grounded tasks, with a public category score of 70.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Does Gemini 3.7 Flash have full benchmark coverage on BenchLM?
No. Gemini 3.7 Flash currently has 55 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Gemini 3.7 Flash?
Gemini 3.7 Flash has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.