GoogleReasoning modelGemini 3.7 Flash
Gemini 3.7 Flash is a Google proprietary reasoning model, released 13 Aug 2026. Its best configuration (medium reasoning effort) ranks #64 of 756 on the BenchLeader Index at 63.4 ±3.4, in the upper half. The ± is the point: 133 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (75) and lowest in reasoning (60). At $1.50 per million tokens blended it is pricier than most ranked models. Output speed of 283 tokens per second puts it in the fastest quarter, with a first answer in 5.6 s. It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 13 Aug 2026.
- Blended price
- $1.50/M
- $0.750 in · $3.75 out
- Output speed
- 283 tok/s
- measured by Artificial Analysis
- First answer
- 5.62 s
- first token 2.50 s
- Context
- 1.0M
- Full answer
- 7.39 s
- median, reasoning included
- Cost per run
- –
- Released
- 13 Aug 2026
- Overall index63
- Reasoning60
- Coding68
- Agents & tools64
- Knowledge73
- Multimodal68
- Long context67
- Composite75
Versions
Google has shipped 13 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Gemini 3.8 Flashmedium | 2 Sept 2026 | 64.7 | #48 |
| Gemini 3.7 Flashmediumthis page | 13 Aug 2026 | 63.4 | #64 |
| Gemini 3.6 Flashhigh | 21 Jul 2026 | 60.5 | #105 |
| Gemini 3.5 Flashmedium | 19 May 2026 | 63.1 | #69 |
| Gemini 3 Flashthinking | 17 Dec 2025 | 59.3 | #125 |
| Gemini 2.5 Flash 09 2025 | 25 Sept 2025 | 51.9 | #318 |
| Gemini 2.5 Flash | 17 Apr 2025 | 52.8 | #289 |
| Gemini 2.0 Flashthinking | 5 Feb 2025 | 45.0 | #499 |
| Gemini 1.5 Flash 002 | 24 Sept 2024 | 40.7 | #628 |
| Gemini 1.5 Flash 001 | 23 May 2024 | 36.4 | #721 |
| Gemini 1.5 Flash 0514 | 14 May 2024 | – | – |
| Gemini 1.5 Flash | – | – | – |
| Gemini Flash 2.0 | – | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | 60.6 | #104 | 290 tok/s | 1.18 s | $0.0014 | Agents & tools 58 · Coding 60 · Composite 72 · Knowledge 72 · Long context 65 · Multimodal 68 · Reasoning 55 |
| mediumbest | 63.4 | #64 | 283 tok/s | 5.62 s | $0.0014 | Agents & tools 64 · Coding 68 · Composite 75 · Knowledge 73 · Long context 67 · Multimodal 68 · Reasoning 60 |
| high | 63.1 | #67 | 303 tok/s | 12 s | $0.0014 | Agents & tools 47 · Coding 63 · Composite 68 · Human preference 69 · Knowledge 68 · Long context 66 · Maths 64 · Multimodal 68 · Reasoning 68 |
| not stated | – | – | 81 tok/s | 2.50 s | $0.0014 | Agents & tools 57 · Coding 58 · Maths 59 |
How its index has moved
8 Sept 2026 to 5 Oct 2026- medium
- high
- low
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
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 | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | 94.8%#5 | – | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | – | – | 1508#19 | – | LMArena | |
| LiveBench Reasoningnot in index | – | – | 87.8%#24 | – | LiveBench | |
| GPQA Diamond (AA)not in index | 90.1%#63 | 92.1%#39 | 94.5%#6 | – | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 35.1%#107 | 39.0%#87 | 47.9%#33 | – | Artificial Analysis | |
| GPQA Diamond (Vals)not in index | – | – | 93.9%#5 | – | Vals AI | |
| ARC-AGI-1 | 85.2%#94 | 91.2%#58 | 95.5%#29 | – | ARC Prize | |
| ARC-AGI-2 | 52.9%#89 | 63.8%#68 | 84.6%#29 | – | ARC Prize | |
| CritPt | 5.7%#129 | 9.4%#108 | 14.3%#87 | – | Artificial Analysis | |
| Chess Puzzlesnot in index | – | – | 47.0%#14 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | 37.0%#15 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | 47.1%#65 | 49.2%#57 | 50.4%#48 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | 93.3%#50 | 94.7%#40 | 96.8%#16 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| SciCode | 53.6%#66 | 59.8%#10 | 56.8%#29 | – | SciCode | |
| FrontierCode | – | – | – | 43.6%#15 | Cognition | |
| LMArena Coding | – | – | 1518#41 | – | LMArena | |
| LMArena WebDev | – | – | 1592#26 | – | LMArena | |
| LiveBench Codingnot in index | – | – | 78.9%#28 | – | LiveBench | |
| SciCode (AA)not in index | 55.7%#42 | 59.8%#10 | 57.2%#28 | – | Artificial Analysis | |
| LiveCodeBench | – | – | 88.7%#5 | – | Vals AI | |
| IOI | – | – | 67.8%#13 | – | Vals AI | |
| SWE-bench (Vals)not in index | – | – | 80.8%#23 | – | Vals AI | |
| Code Migrationnot in index | – | – | 34.8%#32 | – | Vals AI | |
| ProgramBenchnot in index | – | – | 0.0%#23 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | – | 70.4%#32 | – | Vals AI | |
| DeepSWEnot in index | 53.8%#42 | 65.5%#25 | 65.3%#27 | – | Epoch AI Benchmarking Hub | |
| ALE-Benchnot in index | – | – | 904.3#58 | – | Epoch AI Benchmarking Hub | |
| FrontierSWEnot in index | – | – | 20.3%#13 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | – | – | 13.6%#64 | – | Artificial Analysis | |
| Terminal-Bench 2.1 (AA)not in index | 79.8%#46 | 78.3%#52 | 85.8%#24 | – | Artificial Analysis |
Agents & tools
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | 11.2%#73 | – | Terminal-Bench | |
| Remote Labor Index | – | – | – | 5.0%#7 | Scale AI / CAIS | |
| APEX-Agents | – | – | – | 67.8%#5 | Mercor | |
| LMArena Agent | – | – | -1.5#35 | – | LMArena | |
| LiveBench Agentic Codingnot in index | – | – | 58.3%#18 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals) | – | – | 77.5%#14 | – | Vals AI | |
| GDPval (AA)not in index | 40.3%#87 | 42.0%#79 | 43.6%#67 | – | Artificial Analysis | |
| τ²-Bench Banking (AA) | 29.5%#67 | 35.5%#45 | 32.8%#56 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | 60.0%#1 | – | Artificial Analysis | |
| CyberBenchnot in index | – | – | 43.8%#36 | – | Vals AI | |
| Finance Agent v2not in index | – | – | 59.0%#5 | – | Vals AI | |
| Harvey's Legal Agent Benchmarknot in index | – | – | 8.8%#18 | – | Vals AI | |
| Legal Research Benchnot in index | – | – | 34.6%#35 | – | Vals AI | |
| SkillsBenchnot in index | – | – | 65.9%#3 | – | Vals AI | |
| SREBenchnot in index | – | – | 4.6%#9 | – | Vals AI | |
| Tax Agent Benchnot in index | – | – | 57.7%#35 | – | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | – | – | 12.1%#27 | – | Vals AI | |
| Terminal-Bench Sciencenot in index | – | – | 7.1%#15 | – | Vals AI | |
| EnterpriseOps-Gymnot in index | – | 50.4%#2 | – | – | Artificial Analysis | |
| FACTS Searchnot in index | – | – | – | 80.9%#10 |
Maths
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | 71.6%#23 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | 36.6%#30 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | – | 97.2%#30 | – | Epoch AI Benchmarking Hub | |
| ProofBench | – | – | – | 58.0%#19 | Vals AI | |
| LiveBench Mathematicsnot in index | – | – | 93.5%#20 | – | LiveBench | |
| LMArena Maths | – | – | 1503#12 | – | LMArena |
Knowledge
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | 69.2%#9 | – | Epoch AI Benchmarking Hub | |
| LiveBench Data Analysisnot in index | – | – | 68.0%#52 | – | LiveBench | |
| AA-Omniscience | 22.1#54 | 23.7#51 | 26.5#47 | – | Artificial Analysis | |
| MMLU-Pro | – | – | 90.1%#6 | – | Vals AI | |
| LegalBench | – | – | 87.3%#5 | – | Vals AI | |
| TaxEval | – | – | 74.7%#30 | – | Vals AI | |
| Excel Modeling Benchmarknot in index | – | – | 71.3%#11 | – | Vals AI | |
| MedCodenot in index | – | – | 53.4%#9 | – | Vals AI | |
| MedScribenot in index | – | – | 83.9%#37 | – | Vals AI | |
| GDP.pdfnot in index | – | 21.8%#25 | 23.8%#17 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 53.6%#45 | 54.0%#41 | 55.3%#36 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 32.3%#195 | 34.1%#181 | 35.5%#172 | – | Artificial Analysis |
Instruction following
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | – | 85.5%#13 | – | LiveBench | |
| LiveBench Instruction Followingnot in index | – | – | 79.9%#2 | – | LiveBench | |
| LMArena Instruction Followingnot in index | – | – | 1485#17 | – | LMArena |
Human preference
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LMArena Text | – | – | 1488#17 | – | LMArena | |
| LMArena Creative Writingnot in index | – | – | 1493#5 | – | LMArena | |
| LMArena Multi-turnnot in index | – | – | 1493#19 | – | LMArena | |
| LMArena Longer Queriesnot in index | – | – | 1500#13 | – | LMArena |
Multimodal
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| LMArena Vision | – | – | 1315#7 | – | LMArena | |
| MMMU-Pro | 84.9%#14 | 84.7%#15 | 85.5%#10 | – | Artificial Analysis | |
| MMMU-Pro (Vals)not in index | – | – | 89.0%#5 | – | Vals AI | |
| MortgageTaxnot in index | – | – | 66.7%#32 | – | Vals AI | |
| SAGEnot in index | – | – | 49.2%#23 | – | Vals AI |
Long context
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| AA-LCR | 78.7%#101 | 83.0%#24 | 81.7%#46 | – | Artificial Analysis |
Composite
| Benchmark | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | – | – | 157.4#14 | Epoch AI Benchmarking Hub | |
| LiveBench | – | – | 78.8%#15 | – | LiveBench | |
| AA Intelligence Index | 37.0#74 | 39.6#59 | 39.1#64 | – | Artificial Analysis | |
| Vals Indexnot in index | – | – | 51.3#24 | – | Vals AI |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Google AI Studio | 160 tok/s | 2.31 s | $0.375 | $1.88 | 1.0M | – |
| Google AI Studio | 144 tok/s | 2.31 s | $1.35 | $6.75 | 1.0M | – |
| Google AI Studio | 141 tok/s | 2.53 s | $0.750 | $3.75 | 1.0M | – |
| Google Vertex | 129 tok/s | 2.35 s | $1.35 | $6.75 | 1.0M | – |
| Google Vertex | 76 tok/s | 2.79 s | $0.750 | $3.75 | 1.0M | – |
| Google Vertex | 45 tok/s | 16 s | $0.375 | $1.88 | 1.0M | – |
Price history
Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.
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 at $0.075 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0014 | $0.0012 | 6.7 s |
| Summarise a 30-page report | 12,000 / 600 | $0.011 | $0.0052 | 7.7 s |
| Code edit | 6,000 / 1,500 | $0.010 | $0.0071 | 10.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.060 | $0.030 | 19.7 s |
| Structured extraction | 2,000 / 200 | $0.0023 | $0.0012 | 6.3 s |
See also
Data as of 5 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Gemini 3.7 Flash: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/gemini-3-7-flash, data as of 5 Oct 2026.