Models / Gemini 3.8 Flash
Gemini 3.8 Flash
Gemini 3.8 Flash is best for writing, and reasoning and knowledge; pick it when quality matters more than cost. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $3.00.
Results 16 Nov 2026 · 152 results · 12 sources
Test Gemini 3.8 Flash on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $1.50 in · $7.50 out
Google's list price, 10 Nov 2026 · compare prices - Speed
- 141 tokens a second; on its test prompt the answer starts after 15.5 s, thinking time included
Artificial Analysis, on its usual API, at high reasoning - Intelligence Index
- 40.9
Artificial Analysis, at high reasoning; 33.5–40.9 across 3 settings - Spring Prompt overall
- 15th of 36 score 58 of 100 · how it works
- Spring Prompt Score
- 44 of 100 18th of 32 · 5 of 5 benchmarks · our own tests only
- Developer
- Google, based in the US
Weights not published - Released
- 2 Sep 2026
1,048,576 tokens of context - Pricing and availability
- Introductory price: $0.75 in, $3.75 out until 31 Dec 2026
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 25th of 185Claude Opus 5.5 | 15th of 35Claude Fable 5.2 | $3.00 blended, 73rd percentilecheapest: Mistral Nemo | 25th of 65Nemotron 3.5 Super VL |
| Models priced $3–10 per million tokens | 13th of 38Claude Opus 5.5 | 9th of 15Claude Opus 5.5 | sets this group | 4th of 15Mistral Medium 3.5 |
| Models with similar intelligence | sets this group | 1st of 8leads | $3.00 blended, 50th percentilecheapest: MiMo-V2.6-Flash | 5th of 13DeepSeek-V4.1-Flash |
| Models writing 100–200 tokens a second | 5th of 21Claude Sonnet 5.5 | 3rd of 7Muse Wonder | $3.00 blended, 65th percentilecheapest: Qwen3.5-9B | sets this group |
| Models from developers based in the US | 18th of 92Claude Opus 5.5 | 14th of 21Claude Fable 5.2 | $3.00 blended, 53rd percentilecheapest: Gemma 3 4B | 15th of 33Nemotron 3.5 Super VL |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
Measured cost per task
API cost recorded in our benchmark runs, excluding judging.
| Task | Benchmark | Cost per task |
|---|---|---|
| Product listing | CatalogBench | ≈ $0.010 |
| Deck | DeckBench | ≈ $0.061 |
| Survey plan and analysis | SurveyBench | ≈ $0.094 |
| Game of blitz chess | BulletBench | ≈ $0.079 |
Cheapest model that passes
On our benchmarks that define a pass for each task: what one passing answer cost in our run, failed attempts included, and whether a cheaper model passed.
- CatalogBench · cost per 1,000 accepted listings
Gemini 3.8 Flash: $18.79 (92 of 168 attempts), 12 of 25. Cheapest: GPT-6 Luna at $0.70 (114 of 168 attempts). It passed at least as often. - DeckBench · cost per presentable deck
Gemini 3.8 Flash: no presentable decks (0 of 6 tasks). Cheapest: GPT-6.1 Terra at $0.13 (3 of 6 tasks). - SurveyBench · cost per sound survey task
Gemini 3.8 Flash: no sound survey tasks (0 of 9 tasks). Cheapest: GPT-6 Luna at $0.03 (3 of 9 tasks).
Cost per attempt divided by the share that passed, at the run date's prices, excluding judging. Each model at its cheapest setting per passing answer. With a handful of tasks, a pass or two either way is within chance. No estimate where a run had missing outputs, because their cost may not have been recorded.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced $3–10 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| CatalogBenchCatalogBench: reliably publish-ready | 35.7% | 20th of 32 | GPT-6 Astra 75.0% |
| CatalogBenchCatalogBench (sales brief): reliably publish-ready | 3.6% | 23rd of 32 | GPT-6 Astra 69.6% |
Decks from an analysisTurning a finished analysis into a deck you could present as it is
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| DeckBenchDeckBench: deck rating | 788 | 26th of 32 | Qwen4-Max 1,585 |
User surveysPlanning a user survey and reading its results without being misled
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| SurveyBenchSurveyBench: analysis rating | 875 | 16th of 23 | Claude Fable 5.2 1,641 |
Marketing planningPlanning a year of ad spend without overspending
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| ROASBenchROASBench: overall score | 51.4 | 11th of 32 | Claude Fable 5.2 61.3 |
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported | 19.7% | 29th of 107 | Kimi K3.1 Pro 67.2% |
| Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported | 87.6% | 8th of 107 | Claude Fable 5.1 91.4% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 45.8% | 10th of 104 | Grok 4.6 50.7% |
| Vending-Bench 2Vending-Bench 2: money after a year · reported | $5,094 | 25th of 53 | GPT-6 Astra $15,515 |
- tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
- Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
- OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
- Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| APEX-AgentsAPEX-Agents: tasks passed · reported | 64.3% | 8th of 37 | Claude Sonnet 5.5 75.5% |
| GDP.pdfGDP.pdf: professional document tasks · reported | 23.4% | 12th of 31 | GPT-5.6 Sol 30.7% |
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 40.9 | 25th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 47.8% | 18th of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 95.3% | 2nd of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,495 | 7th of 153 | Gemini 4 Argon 1,525 |
| UGI LeaderboardUGI: writing score · reported | 78.6 | 1st of 124 | This model |
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,477 | 14th of 109 | Gemini 4 Argon 1,511 |
| SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported | 69.7% | 7th of 68 | GPT-6 Astra 75.6% |
- Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
| Benchmark | Gemini 3.8 Flash | Rank among available | Best available |
|---|---|---|---|
| BulletBenchBulletBench Lightning 10+1: ladder Elo | 197 | 14th of 18 | Gemini 3.5 Flash-Lite 892 |
| BulletBenchBulletBench Bullet 60s: ladder Elo | 1,068 | 1st of 33 | This model |
Nearest alternatives
- Cheaper at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9Compare with Gemini 3.8 Flash →
- Google's newer, at least as capable modelGemini 4 Argon$4.00 blended · Intelligence Index 52.6Compare with Gemini 3.8 Flash →
- Open weights at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9Compare with Gemini 3.8 Flash →
Against Gemini 3.8 Flash at $3.00 blended, Intelligence Index 40.9. "Similar intelligence" means within 4 points or better.
Where to run it
3 hosts on OpenRouter at the standard service tier, with a median of $1.50 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| not stated | $0.75 | $3.75 | $1.50 | |
| Google AI Studio | not stated | $0.75 | $3.75 | $1.50 |
| not stated | $0.82 | $4.12 | $1.65 |
Other service tiers, not counted above: Google AI Studio flex $0.38 in, $1.88 out; Google flex $0.38 in, $1.88 out; Google AI Studio priority $1.35 in, $6.75 out; Google priority $1.35 in, $6.75 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.
Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| Gemini 3.8 Flash | Claude Opus 5.5 most intelligent at $3–10 per million tokens | MiMo-V2.6-Flash cheapest with similar intelligence | DeepSeek-V4.1-Flash fastest with similar intelligence | Claude Fable 5.2 highest-scoring overall available today | |
|---|---|---|---|---|---|
| Price per million tokens | $3.00 | $8.00 | $0.18 | $0.52 | $16.00 |
| Tokens a second | 141 | 96 | 46 | 369 | – |
| Intelligence Index | 40.9 | 57.6 | 37.9 | 39.5 | – |
| Spring Prompt overall | 58 | 82 | – | 51 | 90 |
| Rank among available models, by use case | |||||
| Product listings | 22nd of 32 | 13th | – | 15th | 5th |
| Decks from an analysis | 26th of 32 | 7th | – | – | 4th |
| User surveys | 16th of 23 | 4th | – | – | 1st |
| Marketing planning | 11th of 32 | 9th | – | – | 1st |
| Agents and tool use | 35th of 159 | 3rd | 42nd | 31st | – |
| Professional work | 11th of 51 | 3rd | – | – | – |
| Reasoning and knowledge | 15th of 187 | 1st | 55th | 42nd | – |
| Writing | 3rd of 169 | 5th | 56th | 29th | – |
| Sticking to the facts | 12th of 139 | 3rd | 46th | 23rd | – |
| Speed under pressure | 13th of 35 | – | – | – | 8th |
| Side by side → | Side by side → | Side by side → | Side by side → | ||
Shaded figures are better than Gemini 3.8 Flash's. A dash means no result.
Research and examples
- Gemini 4 Hydrogen got faster: we reran our speed chess test
- Muse Ember review: GPT-6 Luna's price, better at analysis, and no Gemini Flash against a clock
- Kimi K3.1 Pro first look: the best open-weight model on our board, and very slow
In the playground: our pick in 0 of 20 tests, 72% of checks passed →
- The solar system, to scale in time (3 of 3 checks)
- A product page from one feed row (5 of 5 checks)
- A pricing table with a monthly/yearly switch (4 of 4 checks)
Where it has been measured
Highest-scoring overall of the 8 models with similar intelligence. 13th most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for 4 of the 10 use cases measured, led by writing, and reasoning and knowledge; in the bottom quarter for decks from an analysis.
- BulletBench20 results
- CatalogBench31 results
- DeckBench17 results
- ROASBench9 results
- SurveyBench21 results
- APEX-Agents1 result
- Arena (formerly LMArena)11 results
- Artificial Analysis29 results
- GDP.pdf2 results
- SimpleQA Verified (Epoch AI)1 result
- UGI Leaderboard9 results
- Vending-Bench 21 result
- Berkeley Function Calling Leaderboard (BFCL) V4Pending: latest results 16 Dec 2025
- Microsoft STATE-BenchPending: latest results 1 Jul 2026
- OpenHands IndexPending: latest results 30 Jun 2026
- tau2-benchPending: latest results 3 Aug 2026
- Remote Labor IndexNot measured
- Vectara Hallucination LeaderboardNot measured
Every result
152 published results from 12 sources, each in the source's own units, with the configuration that produced it.
BulletBench · measured by Spring Prompt · 20 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| BulletBench Blitz 3+2: cost per gameUS dollars, lower is better | $0.0795 | 12 of 22 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| BulletBench Blitz 3+2: games lost on time% of games, lower is better | 12.5% | 7 of 22 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| BulletBench Blitz 3+2: invalid moves% of moves, lower is better | 0.0% | 1 of 22 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| BulletBench Blitz 3+2: ladder Eloladder Elo, higher is better | 1,126 949–1,347 |
2 of 22 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| BulletBench Blitz 3+2: median move timemilliseconds, lower is better | 4.0 s | 9 of 22 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| BulletBench Bullet 60s: cost per gameUS dollars, lower is better | $0.0154 | 46 of 71 | Gemini 3.8 Flash provider default reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: cost per gameUS dollars, lower is better | $0.0165 | 49 of 71 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: games lost on time% of games, lower is better | 58.3% | 47 of 71 | Gemini 3.8 Flash provider default reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: games lost on time% of games, lower is better | 50.0% | 41 of 71 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: invalid moves% of moves, lower is better | 0.0% | 1 of 71 | Gemini 3.8 Flash provider default reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: invalid moves% of moves, lower is better | 0.0% | 1 of 71 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: ladder Eloladder Elo, higher is better | 529 263–688 |
27 of 71 | Gemini 3.8 Flash provider default reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: ladder Eloladder Elo, higher is better | 1,068 888–1,241 |
1 of 71 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: median move timemilliseconds, lower is better | 2.8 s | 56 of 71 | Gemini 3.8 Flash provider default reasoning |
1 Oct 2026 |
| BulletBench Bullet 60s: median move timemilliseconds, lower is better | 1.8 s | 48 of 71 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Lightning 10+1: cost per gameUS dollars, lower is better | $0.0041 | 30 of 48 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Lightning 10+1: games lost on time% of games, lower is better | 83.3% | 43 of 48 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Lightning 10+1: invalid moves% of moves, lower is better | 0.0% | 1 of 48 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better | 197 0–439 |
41 of 48 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
| BulletBench Lightning 10+1: median move timemilliseconds, lower is better | 1.8 s | 47 of 48 | Gemini 3.8 Flash (low reasoning) low reasoning |
1 Oct 2026 |
Not shown: Not your cost: prices are those charged on the run date.
CatalogBench · measured by Spring Prompt · 31 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| CatalogBench (sales brief): channel rules broken% of products, lower is better | 0.6% | 17 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): claims to check% of products, lower is better | 5.4% | 26 of 32 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): content quality% of checks, higher is better | 97.6% | 14 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): failed outputs% of products, lower is better | 0.0% | 1 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): missing UK information% of products, lower is better | 0.0% | 1 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): not findable% of products, lower is better | 8.9% | 30 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): publish-ready listings% of products, higher is better | 16.7% | 23 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): reliably publish-ready% of products, higher is better | 3.6% | 23 of 34 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): unsupported claims% of products, lower is better | 81.6% | 29 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): unsupported claimsclaims per product, lower is better | 3.08 | 25 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): wrong attributes% of products, lower is better | 11.9% | 2 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench (sales brief): wrong category or variant% of products, lower is better | 3.0% | 24 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: channel compliance% of products, higher is better | 99.4% | 26 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: channel rules broken% of products, lower is better | 0.6% | 20 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: claims to check% of products, lower is better | 0.0% | 1 of 32 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: conflicts caught% of conflicts, higher is better | 100.0% | 1 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: content quality% of checks, higher is better | 97.7% | 9 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: cost per productUS dollars, lower is better | $0.0103 | 19 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: decision accuracy% of decisions, higher is better | 96.4% | 19 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: failed outputs% of products, lower is better | 0.0% | 1 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: field accuracy% of missing fields, higher is better | 92.7% | 24 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: invented values% of filled values, lower is better | 0.3% | 4 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: missing UK information% of products, lower is better | 0.0% | 1 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: not findable% of products, lower is better | 8.3% | 29 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: publish-ready listings% of products, higher is better | 54.8% | 21 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: reliably publish-ready% of products, higher is better | 35.7% | 20 of 34 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: time per productseconds, lower is better | 18.7 | 19 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: unsupported claims% of products, lower is better | 31.6% | 25 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: unsupported claimsclaims per product, lower is better | 0.79 | 23 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: wrong attributes% of products, lower is better | 15.5% | 11 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
| CatalogBench: wrong category or variant% of products, lower is better | 3.6% | 27 of 35 | Gemini 3.8 Flash provider default reasoning |
30 Sep 2026 |
Not shown: Not your catalogue: invented products with generated images, so a model's result on your own feed can differ.
DeckBench · measured by Spring Prompt · 17 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| DeckBench: accurate decks% of tasks, higher is better | 16.7% | 25 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: caveat dropped% of tasks, lower is better | 0.0% | 1 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: clean layout% of tasks, higher is better | 16.7% | 24 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: cost per deckUS dollars, lower is better | $0.0613 | 16 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: deck ratingrating, higher is better | 788 719–842 |
27 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: design quality% of the maximum, higher is better | 61.7% | 19 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: draft figure quoted% of tasks, lower is better | 50.0% | 27 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: findings missing% of tasks, lower is better | 0.0% | 1 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: head-to-head win rate% of comparisons, higher is better | 38.7% | 27 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: layout defects% of tasks, lower is better | 83.3% | 24 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: misleading metric used% of tasks, lower is better | 0.0% | 1 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: presentable decks% of tasks, higher is better | 0.0% | 15 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: recommendation late or wrong% of tasks, lower is better | 33.3% | 20 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: slides needing work% of tasks, lower is better | 33.3% | 10 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: time per deckseconds, lower is better | 93.0 | 13 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: unsupported claims% of tasks, lower is better | 50.0% | 30 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
| DeckBench: unsupported numbers% of tasks, lower is better | 16.7% | 26 of 34 | Gemini 3.8 Flash provider default reasoning |
6 Oct 2026 |
Not shown: Not your analysis or your brand: invented companies, six public tasks, one deck per model per task at the provider's default reasoning setting.
ROASBench · measured by Spring Prompt · 9 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| ROASBench: audience scorescore out of 100, higher is better | 67.1 | 10 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: business scorescore out of 100, higher is better | 51.0 | 11 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: consistency scorescore out of 100, higher is better | 36.4 | 6 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: contribution profitsimulated US dollars, higher is better | $842,432 | 5 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: cost of a runUS dollars, lower is better | $0.16 | 16 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: months over budgetmonths of 12, lower is better | 0 | 1 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: overall scorescore out of 100, higher is better | 51.4 | 11 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: planning scorescore out of 100, higher is better | 54.7 | 21 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
| ROASBench: return on ad spendprofit per $1 spent, higher is better | $0.65 | 12 of 35 | Gemini 3.8 Flash provider default reasoning |
29 Sep 2026 |
Not shown: Not real ad performance: the market is a deterministic simulation of one invented skincare brand.
SurveyBench · measured by Spring Prompt · 21 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| SurveyBench: analysis ratingrating, higher is better | 875 794–943 |
16 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: analysis scorepoints of 100, higher is better | 74.7 | 15 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: cost per taskUS dollars, lower is better | $0.0943 | 14 of 24 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: head-to-head win rate% of comparisons, higher is better | 62.5% | 6 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: leading or double-barrelled questions% of tasks, lower is better | 66.7% | 21 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: mistaken next steps% of tasks, lower is better | 11.1% | 5 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: numbers right% of answers, higher is better | 100.0% | 1 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: objectives unanswerable% of tasks, lower is better | 0.0% | 1 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: output tokens per tasktokens, lower is better | 21,981 | 3 of 14 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: precision ignored% of tasks, lower is better | 44.4% | 18 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: research scorepoints of 100, higher is better | 77.6 | 15 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: sound research% of tasks, higher is better | 0.0% | 15 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: stakeholder's view presumed% of tasks, lower is better | 22.2% | 15 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: survey plan scorepoints of 100, higher is better | 84.4 | 18 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: survey structure% of tasks, lower is better | 22.2% | 11 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: time per taskseconds, lower is better | 131 | 8 of 24 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: traps handled% of traps, higher is better | 78.3% | 18 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: traps missed% of tasks, lower is better | 88.9% | 16 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: unsupported findings% of tasks, lower is better | 77.8% | 14 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: wrong numbers% of tasks, lower is better | 0.0% | 1 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
| SurveyBench: wrong recommendation% of tasks, lower is better | 0.0% | 1 of 25 | Gemini 3.8 Flash provider default reasoning |
10 Nov 2026 |
Not shown: Not your customers or your data: invented organisations with simulated respondents, nine public tasks, one run per model per task at the provider's default reasoning setting.
APEX-Agents · reported by APEX-Agents · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| APEX-Agents: tasks passed% of tasks, higher is better | 64.3% | 8 of 39 | Gemini 3.8 Flash | 1 Oct 2026 |
Not shown: Not your firm's documents or tools; graded by rubric, not by a client.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Agent: confirmed task successIPS effect estimate, higher is better | 0.07 0.05–0.09 |
12 of 50 | Gemini 3.8 Flash (high reasoning, arena agent) | 2 Oct 2026 |
| Arena Agent: praise over complaintIPS effect estimate, higher is better | 0.05 0.02–0.08 |
20 of 50 | Gemini 3.8 Flash (high reasoning, arena agent) | 2 Oct 2026 |
| Arena Agent: steerabilityIPS effect estimate, higher is better | 0.03 0.02–0.04 |
18 of 50 | Gemini 3.8 Flash (high reasoning, arena agent) | 2 Oct 2026 |
| Arena Agent: tool groundingIPS effect estimate, higher is better | 0.00 0.00–0.00 |
18 of 50 | Gemini 3.8 Flash (high reasoning, arena agent) | 2 Oct 2026 |
| Arena Text factuality: overallArena rating, higher is better | 1,477 1,472–1,481 |
19 of 182 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,481 1,472–1,490 |
26 of 406 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,485 1,476–1,494 |
7 of 411 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,526 1,515–1,537 |
16 of 363 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,486 1,479–1,493 |
15 of 413 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,495 1,490–1,500 |
8 of 413 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,487 1,479–1,495 |
9 of 412 | Gemini 3.8 Flash (high reasoning) | 2 Oct 2026 |
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Artificial Analysis · reported by Artificial Analysis · 29 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 76.3 | 18 of 187 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 73.5 | 35 of 187 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 74.1 | 33 of 187 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 40.9 | 56 of 413 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 33.5 | 101 of 413 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 39.8 | 61 of 413 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 95.3% | 3 of 360 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 92.0% | 42 of 360 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 93.5% | 14 of 360 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 47.8% | 37 of 419 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 37.1% | 108 of 419 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 42.1% | 75 of 419 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 81.3% | 53 of 407 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 80.7% | 64 of 407 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 84.0% | 11 of 407 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 141 | 44 of 137 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 56.6% | 34 of 205 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 55.0% | 54 of 205 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 55.1% | 51 of 205 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 87.6% | 18 of 188 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 83.1% | 36 of 188 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 83.9% | 34 of 188 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 19.7% | 69 of 204 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 10.1% | 96 of 204 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 19.7% | 69 of 204 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 15.5 | 77 of 137 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 44.9% | 16 of 175 | Gemini 3.8 Flash (high reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 33.2% | 52 of 175 | Gemini 3.8 Flash (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 45.8% | 13 of 175 | Gemini 3.8 Flash (medium reasoning) | 20 Oct 2026 |
Not shown: Not your codebase or tools.
GDP.pdf · reported by GDP.pdf · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| GDP.pdf: professional document tasks% of rubric, higher is better | 23.2% | 18 of 49 | Gemini 3.8 Flash (high reasoning) | 1 Oct 2026 |
| GDP.pdf: professional document tasks% of rubric, higher is better | 23.4% | 17 of 49 | Gemini 3.8 Flash (medium reasoning) | 1 Oct 2026 |
Not shown: Not your documents; 100 tasks, so small differences are noise.
SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| SimpleQA Verified: correct answers% of questions, higher is better | 69.7% | 7 of 85 | Gemini 3.8 Flash (high reasoning) | 2 Sep 2026 |
Not shown: Not answers grounded in your documents; tests what the model remembers.
UGI Leaderboard · reported by UGI Leaderboard · 9 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| UGI: requested-length error% off the requested word count, lower is better | 13.0% | 111 of 379 | Gemini 3.8 Flash (high reasoning) | 3 Sep 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 16.0% | 135 of 379 | Gemini 3.8 Flash (low reasoning) | 3 Sep 2026 |
| UGI: requested-length error% off the requested word count, lower is better | 14.0% | 119 of 379 | Gemini 3.8 Flash (medium reasoning) | 3 Sep 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.34 | 238 of 379 | Gemini 3.8 Flash (high reasoning) | 3 Sep 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.32 | 294 of 379 | Gemini 3.8 Flash (low reasoning) | 3 Sep 2026 |
| UGI: style adherencescore from 0 to 1, higher is better | 0.34 | 247 of 379 | Gemini 3.8 Flash (medium reasoning) | 3 Sep 2026 |
| UGI: writing scorescore out of 100, higher is better | 72.0 | 13 of 379 | Gemini 3.8 Flash (high reasoning) | 3 Sep 2026 |
| UGI: writing scorescore out of 100, higher is better | 72.7 | 7 of 379 | Gemini 3.8 Flash (low reasoning) | 3 Sep 2026 |
| UGI: writing scorescore out of 100, higher is better | 78.6 | 1 of 379 | Gemini 3.8 Flash (medium reasoning) | 3 Sep 2026 |
Not shown: Not other format limits such as character counts or bullet counts.
Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vending-Bench 2: money after a yearUS dollars, higher is better | $5,094 | 26 of 63 | Gemini 3.8 Flash | 1 Oct 2026 |
Not shown: Not a real business; one simulated market with set rules.
Embed a score badge
A badge for its Spring Prompt Score and each of our benchmarks that ranked Gemini 3.8 Flash, from the current results. Paste the code into a page or README; it links back to where the result comes from.
Spring Prompt Score · 5 of 5 benchmarks
<a href="https://springprompt.com/score#google-gemini-3-8-flash"><img src="https://springprompt.com/badge/score/google-gemini-3-8-flash.svg" alt="Gemini 3.8 Flash is #18 of 32 on the Spring Prompt Score (44 of 100, from 5 of 5 of our benchmarks), measured by Spring Prompt" height="20"></a>
CatalogBench · Reliably publish-ready, factual brief
<a href="https://springprompt.com/benchmarks/catalogbench?focus=google-gemini-3-8-flash"><img src="https://springprompt.com/badge/catalogbench/google-gemini-3-8-flash.svg" alt="Gemini 3.8 Flash is #20 of 32 on CatalogBench (Reliably publish-ready, factual brief: 35.7%), measured by Spring Prompt" height="20"></a>
DeckBench · Deck rating
<a href="https://springprompt.com/benchmarks/deckbench?focus=google-gemini-3-8-flash"><img src="https://springprompt.com/badge/deckbench/google-gemini-3-8-flash.svg" alt="Gemini 3.8 Flash is #26 of 33 on DeckBench (Deck rating: 788), measured by Spring Prompt" height="20"></a>
SurveyBench · Analysis rating
<a href="https://springprompt.com/benchmarks/surveybench?focus=google-gemini-3-8-flash"><img src="https://springprompt.com/badge/surveybench/google-gemini-3-8-flash.svg" alt="Gemini 3.8 Flash is #16 of 24 on SurveyBench (Analysis rating: 875), measured by Spring Prompt" height="20"></a>
ROASBench · Score
<a href="https://springprompt.com/benchmarks/roasbench?focus=google-gemini-3-8-flash"><img src="https://springprompt.com/badge/roasbench/google-gemini-3-8-flash.svg" alt="Gemini 3.8 Flash is #11 of 33 on ROASBench (Score: 51.4), measured by Spring Prompt" height="20"></a>
BulletBench · Lightning 10+1
<a href="https://springprompt.com/benchmarks/bulletbench?focus=google-gemini-3-8-flash"><img src="https://springprompt.com/badge/bulletbench/google-gemini-3-8-flash.svg" alt="Gemini 3.8 Flash is #40 of 45 on BulletBench (Lightning 10+1: 197), measured by Spring Prompt" height="20"></a>
Will Gemini 3.8 Flash work for your product?
Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.
New here? Your email starts a free trial. No credit card needed.