# Gemini 3 Flash Preview

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-3-flash-preview. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-3-flash-preview.

Google

Canonical URL: https://benchize.com/models/gemini-3-flash-preview
Last updated: Thu, 22 Oct 2026 06:20:09 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Google

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,184elo | — | 43 / 110 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1184 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics averageGenerationTimeMs 24388 battles 467 losses 174 standardError Not reported winRate 62.7 wins 293 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/71` |  |  |  |  |  |  |  |
| [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 1,063elo | SE ±7.88 | 25 / 31 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1063 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics Uncertainty Standard error: ±7.88 averageGenerationTimeMs Not reported battles 2359 losses 1241 standardError 7.8798 winRate 47.4 wins 1118 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/37` |  |  |  |  |  |  |  |
| [Agent Poker Bench / overall](https://benchize.com/benchmarks/vals-ai%3Apoker_agent%3Aoverall.md) | 1,100.21source score | SE ±0 | 1 / 2 | $0.00873 | 7.71source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_poker_agent.BeZvaV0m.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 1100.2125195039544 \| source_score \| reported \| Higher is better \| \| `cost_per_test` \| 0.00872674530884417 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.7072606111437345 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Not reported reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 sourcePopulation 17 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_poker_agent.BeZvaV0m.json) Source Vals AI Original model label google/gemini-3-flash-preview Source version 1 Observed 2026-10-22T02:10:31.828Z Evidence SHA-256 `23821a0049c3ab8467573a74dac6c5037748e301e2abcd91885ec708168335af` Source locator `/tasks/overall/google~1gemini-3-flash-preview` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / swebench](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aswebench.md) | 68.63% | SE ±4.59 pp | 17 / 20 | $0.31 | 327.17source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.627 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.306186 \| USD \| per_test \| Lower is better \| \| `latency` \| 327.172 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Not reported reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.59 pp sourcePopulation 33 stderr 4.594 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label google/gemini-3-flash-preview Source version 1.2 Observed 2026-10-22T02:10:07.406Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/swebench/google~1gemini-3-flash-preview` |  |  |  |  |  |  |  |
| [DesignArena Image to web application](https://benchize.com/benchmarks/designarena%3Aimage-to-webapp.md) | 1,064elo | SE ±17.42 | 24 / 24 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1064 \| elo \| image-to-webapp \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality image sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics Uncertainty Standard error: ±17.42 averageGenerationTimeMs Not reported battles 479 losses 285 standardError 17.4152 winRate 40.5 wins 194 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:37:59.412Z Evidence SHA-256 `cc4e49fc057d3b786184ff44b697422e2420a174e8a98a80a77aa65021921ab4` Source locator `/data/31` |  |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,655 | — | 15 / 191 | — | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1655 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemini_3_flash_preview ### Reported statistics coverageCount 27 draws 9 judged 209 losses 60 rank 20 ratingDeviation 28 wins 140 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemini 3 Flash Preview Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/19` |  |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 55.7% | — | 63 / 93 | — | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 55.7 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 14.63 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 13.46 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 12.28 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 11.48 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 10.93 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 11.11 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 10.77 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 11.18 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 12.39 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion gemini-3-flash-preview ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label gemini-3-flash-preview Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/39` |  |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,166elo | — | 60 / 117 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1166 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics averageGenerationTimeMs 35557 battles 369 losses 154 standardError Not reported winRate 58.3 wins 215 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/93` |  |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,189elo | SE ±5.4 | 50 / 116 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1189 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics Uncertainty Standard error: ±5.4 averageGenerationTimeMs 34497 battles 4414 losses 1870 standardError 5.3957 winRate 57.6 wins 2544 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/80` |  |  |  |  |  |  |  |
| [FrontierMath Tiers 1–3 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tiers_1_3_v2.md) | 51.23% | SE ±2.97 pp | 29 / 50 | — | — | [epoch ai · FrontierMath-Tiers-1-3-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.512280701754386 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.512280701754386 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tiers-1-3-v2-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±2.97 pp standardError 0.02966059084324674 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tiers_1_3_v2.csv) Source epoch ai Original model label gemini-3-flash-preview Source version FrontierMath-Tiers-1-3-v2-Private Evaluated 2026-06-11T23:44:30.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `d3458d4272f99e04212525904a59fffffa7a94e827c62b26e36e3fd3e15fe587` Source locator `/rows/104` |  |  |  |  |  |  |  |
| [DesignArena Native Android development](https://benchize.com/benchmarks/designarena%3Aandroid.md) | 1,057elo | — | 21 / 23 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=android) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1057 \| elo \| android \| Higher is better \| ### Configuration arenaType agents category nativeapps inputModality Not reported sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 720 losses 374 standardError Not reported winRate 48.1 wins 346 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=android) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:38:03.000Z Evidence SHA-256 `d9d0cd4bea54b696c28f907a98ba42ebf8dd4da9da201b6c70c95f76de35f525` Source locator `/data/32` |  |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,196elo | — | 53 / 123 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1196 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics averageGenerationTimeMs 35775 battles 3461 losses 1488 standardError Not reported winRate 57 wins 1973 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/84` |  |  |  |  |  |  |  |
| [FrontierMath Tier 4 (2025-07-01 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4.md) | 4.17% | SE ±2.91 pp | 8 / 15 | — | — | [epoch ai · FrontierMath-Tier-4-2025-07-01-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.041666666666666664 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.041666666666666664 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-2025-07-01-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±2.91 pp standardError 0.02914766351555603 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4.csv) Source epoch ai Original model label gemini-3-flash-preview Source version FrontierMath-Tier-4-2025-07-01-Private Evaluated 2025-12-17T22:40:29.476Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `c928e5adccd6e0995d50ede183fb99728d6c5be01951434a3077429ffb5802b2` Source locator `/rows/30` |  |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 83.21% | SE ±1.9 pp | 64 / 126 | — | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8320707070707071 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.8320707070707071 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±1.9 pp standardError 0.019036353018587762 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label gemini-3-flash-preview Source version GPQA diamond Evaluated 2025-12-17T22:39:00.278Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `9ef0b938bdd8406b029d595983ee8ad3a80bd9d64b82605b91b5ce39ba650c39` Source locator `/rows/183` |  |  |  |  |  |  |  |
| [MCP Atlas](https://benchize.com/benchmarks/scale%3Amcp_atlas.md) | 62source score | CI 59–65 | 16 / 22 | — | — | [scale](https://labs.scale.com/leaderboard/mcp_atlas) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 62 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-3-flash-preview sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 59–65 contaminationWarning Not reported rank 27 reportedConfidenceHalfWidth 3 ### Source [Original source](https://labs.scale.com/leaderboard/mcp_atlas) Source scale Original model label gemini-3-flash-preview Observed 2026-10-22T03:30:07.875Z Evidence SHA-256 `7b0bc178e35a1688340e9efca5795a8f54d07e56a98f9cacd5e4471e0da266e9` Source locator `/rows/26` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 85.47% | — | 93 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.47 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.04 \| percent \| category \| Higher is better \| \| `creative_writing` \| 75.04 \| percent \| category \| Higher is better \| \| `language` \| 95 \| percent \| category \| Higher is better \| \| `utility` \| 86.39 \| percent \| category \| Higher is better \| \| `reasoning` \| 80.99 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.54 \| percent \| category \| Higher is better \| \| `rule_following` \| 65.14 \| percent \| category \| Higher is better \| \| `hallucination` \| 85.61 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3 Flash (Preview) thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3 Flash (Preview) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/121` |  |  |  |  |  |  |  |
| [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,090elo | SE ±8.67 | 30 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1090 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics Uncertainty Standard error: ±8.67 averageGenerationTimeMs Not reported battles 2015 losses 1076 standardError 8.6659 winRate 46.6 wins 939 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/45` |  |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 46.12% | CI 42.5–53.67% | 26 / 38 | — | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.461171 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Confidence interval: 42.5–53.67% confidenceIntervalHigh 0.536712 confidenceIntervalLow 0.424996 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label gemini-3-flash-preview Source version judgemark-v4 Observed 2026-10-22T05:10:06.884Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/28` |  |  |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 85.38% | — | 5 / 39 | — | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 85.38 \| percent \| overall \| Higher is better \| \| `stability` \| 0.78 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.895 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.761 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion gemini-3-flash-preview ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label gemini-3-flash-preview Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/29` |  |  |  |  |  |  |  |
| [SWE-bench Verified (Epoch AI)](https://benchize.com/benchmarks/epoch-ai%3Aswe_bench_verified.md) | 75.41% | SE ±1.96 pp | 6 / 10 | — | — | [epoch ai · SWE-Bench verified](https://epoch.ai/data/benchmark_data.zip#file=swe_bench_verified.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7541322314049587 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.7541322314049587 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion SWE-Bench verified reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±1.96 pp standardError 0.019593002139508684 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=swe_bench_verified.csv) Source epoch ai Original model label gemini-3-flash-preview Source version SWE-Bench verified Evaluated 2026-02-18T20:12:36.725Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `6480176a5d9b1573676fcacc5df5e8c58f9e5fce34025600a19b3bf60617561c` Source locator `/rows/14` |  |  |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 61.1% | — | 24 / 62 | — | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.1 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3 Flash Preview thinkingEnabled Not reported ### Reported statistics rank 33rd ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label Gemini 3 Flash Preview Observed 2026-10-22T03:40:04.693Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/34` |  |  |  |  |  |  |  |
| [FrontierMath Tier 4 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2.md) | 17.07% | SE ±5.95 pp | 35 / 39 | — | — | [epoch ai · FrontierMath-Tier-4-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.17073170731707318 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.17073170731707318 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±5.95 pp standardError 0.05949419959829497 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label gemini-3-flash-preview Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-06-11T23:44:30.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `2bbef8e82ac84071e3ce42bf744f4fc39dff04a549ccb1a288e3800918bc2e55` Source locator `/rows/60` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,110elo | SE ±6.07 | 32 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1110 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion gemini-3-flash-preview variationName public ### Reported statistics Uncertainty Standard error: ±6.07 averageGenerationTimeMs Not reported battles 3979 losses 2049 standardError 6.0704 winRate 48.5 wins 1930 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label Gemini 3 Flash Preview Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/44` |  |  |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 92.78% | SE ±3.52 pp | 40 / 124 | — | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9277777777777778 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9277777777777778 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±3.52 pp standardError 0.035196259111492545 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label gemini-3-flash-preview Source version OTIS Mock AIME 2024-2025 Evaluated 2025-12-17T22:40:30.896Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/190` |  |  |  |  |  |  |  |
| [FrontierMath (2025-02-28 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath.md) | 35.64% | SE ±2.82 pp | 7 / 18 | — | — | [epoch ai · FrontierMath-2025-02-28-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.356401384083045 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.356401384083045 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-2025-02-28-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3-flash-preview ### Reported statistics Uncertainty Standard error: ±2.82 pp standardError 0.028221558784583784 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) Source epoch ai Original model label gemini-3-flash-preview Source version FrontierMath-2025-02-28-Private Evaluated 2025-12-17T22:40:29.699Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `f5c92f0f0b9103abb02308fd428c0806e7c21b91e8a14d43edb8af77ce941598` Source locator `/rows/29` |  |  |  |  |  |  |  |

---
Cite as: Gemini 3 Flash Preview — Benchize, https://benchize.com/models/gemini-3-flash-preview (retrieved 2026-10-22)