# Gemini 3.6 Flash

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-3-6-flash. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-3-6-flash.

Google

Canonical URL: https://benchize.com/models/gemini-3-6-flash
Last updated: Wed, 21 Oct 2026 18:05:10 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 Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 1,181elo | SE ±7.04 | 19 / 31 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1181 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±7.04 averageGenerationTimeMs Not reported battles 2936 losses 1635 standardError 7.0433 winRate 44.3 wins 1301 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/24` |  |  |  |  |  |  |  |
| [TubeLab Scriptwriting](https://benchize.com/benchmarks/tubelab%3Ascriptwriting.md) | 75% | — | 14 / 16 | 0.43ratio | — | [tubelab](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `quality` \| 75 \| percent \| source_reported \| Higher is better \| \| `craft` \| 75 \| percent \| source_reported \| Higher is better \| \| `relative_cost_per_script` \| 0.43 \| ratio \| source_reported \| Lower is better \| \| `script_time` \| 3.9 \| minutes \| source_reported \| Lower is better \| \| `hook` \| 8 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `retention` \| 7.5 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `storytelling` \| 6.9 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `voiceMatch` \| 7.2 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `pacing` \| 7.2 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `clarity` \| 8.3 \| score_out_of_10 \| craft_rubric \| Higher is better \| ### Configuration judgingProtocol blind_model_judges Reasoning effort unknown taskCount 12 ### Reported statistics confidence {"high":78.8,"low":71} headToHead {"losses":9,"ties":1,"winPercent":21,"wins":2} rank 19 ### Source [Original source](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) Source tubelab Original model label Gemini 3.6 Flash Observed 2026-10-21T16:34:03.856Z Evidence SHA-256 `72f9d867f388256af8fc6dca12e8c7b6f1ddcbb97f0712da339b73102686761f` Source locator `/rows/18` |  |  |  |  |  |  |  |
| [DesignArena Agentic HTML slide generation](https://benchize.com/benchmarks/designarena%3Aagentic-html-slides.md) | 1,148elo | — | 9 / 13 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-html-slides) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1148 \| elo \| agentic-html-slides \| Higher is better \| ### Configuration arenaType agents category agon_slides_html inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 1261 losses 733 standardError Not reported winRate 41.9 wins 528 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-html-slides) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:04.391Z Evidence SHA-256 `02fccc0ebb2758ba116665bc1fcb2f049b9b2f1251c0f0bb29caed69ffaf0cb0` Source locator `/data/16` |  |  |  |  |  |  |  |
| [Kangaroo 2025 9-10](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_9-10.md) | 100% | 95% CI 100–100% | 1 / 15 | 0.03usd per problem | — | [matharena · kangaroo--kangaroo_2025_9-10](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.025 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_9-10 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 100–100% confidenceInterval95 0.00 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_9-10 Observed 2026-10-21T16:52:33.536Z Evidence SHA-256 `52964b89ab1a06cf2e79ec946b33004aa40ca31f1ec26888e6dd0f0a7994223a` Source locator `/table/rows/0` |  |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,272elo | — | 24 / 110 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1272 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 64656 battles 7925 losses 3733 standardError Not reported winRate 52.9 wins 4192 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/33` |  |  |  |  |  |  |  |
| [Kangaroo 2025 3-4](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_3-4.md) | 68.75% | 95% CI 55.64–81.86% | 6 / 16 | 0.06usd per problem | — | [matharena · kangaroo--kangaroo_2025_3-4](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.75 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.062 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_3-4 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 55.64–81.86% confidenceInterval95 13.11 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_3-4 Observed 2026-10-21T16:52:32.012Z Evidence SHA-256 `38fec99c55752fef6703c9ed49d9e1e204b235f2bd78d5ee47725dac9e5da89c` Source locator `/table/rows/7` |  |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,297elo | — | 21 / 112 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1297 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 66030 battles 1885 losses 871 standardError Not reported winRate 53.8 wins 1014 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/26` |  |  |  |  |  |  |  |
| [OfficeQA Pro V2 — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Av2-agent.md) | 12.2% | — | 7 / 7 | — | — | [officeqa pro · sha256:d97762a15ad277575c2f567c4e3a318b6bb1d4e4d4d0008cd4f5c7953bae3253](https://api.github.com/repos/databricks/officeqa/git/blobs/cebf9bca23960fa1328f3421f0cb28d236cd86eb) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 12.2 \| percent \| agent_full_tools \| Higher is better \| ### Configuration harness Gemini Antigravity ### Reported statistics sampleSize 90 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/cebf9bca23960fa1328f3421f0cb28d236cd86eb) Source officeqa pro Original model label Gemini 3.6 Flash Source version sha256:d97762a15ad277575c2f567c4e3a318b6bb1d4e4d4d0008cd4f5c7953bae3253 Observed 2026-10-21T16:34:42.395Z Evidence SHA-256 `0e566748b11c0bfc76d6076b7d871f45fe43266e4787dfe523c359f3db0b7a10` Source locator `/chart-labels/1` |  |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,080.7 | Range 1,036.7–1,123.8 | 99 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1080.7 \| rating \| reported \| Higher is better \| \| `overall` \| 69.28 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 60.13 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 69.62 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 71.77 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 74.16 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 82.77 \| source_score \| rubric \| Higher is better \| \| `slop` \| 74.79 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 89.46 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 71.27 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 58.78 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 66.34 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 70.02 \| source_score \| rubric \| Higher is better \| ### Configuration provider google Reasoning effort unknown scoreScope 10_task_current sourceConfiguration gemini-3-6-flash ### Reported statistics Uncertainty Reported interval: 1,036.7–1,123.8 interval [1036.7,1123.8] rank 103 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Gemini 3.6 Flash (medium thinking) Evaluated 2026-10-11 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/102` |  |  |  |  |  |  |  |
| [DesignArena Image to web application](https://benchize.com/benchmarks/designarena%3Aimage-to-webapp.md) | 1,177elo | SE ±17.85 | 16 / 24 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1177 \| elo \| image-to-webapp \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality image sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±17.85 averageGenerationTimeMs Not reported battles 385 losses 205 standardError 17.851 winRate 46.8 wins 180 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:59.412Z Evidence SHA-256 `cc4e49fc057d3b786184ff44b697422e2420a174e8a98a80a77aa65021921ab4` Source locator `/data/18` |  |  |  |  |  |  |  |
| [BrokenArXiv 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--june.md) | 12.04% | 95% CI 5.9–18.18% | 20 / 21 | 0.15usd per problem | — | [matharena · arxiv_false--june](https://matharena.ai/competition_tables/arxiv_false--june) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 12.04 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.15 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--june predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 5.9–18.18% confidenceInterval95 6.14 problems 54 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--june) Source matharena Original model label Gemini 3.6 Flash Source version arxiv_false--june Observed 2026-10-21T16:52:25.323Z Evidence SHA-256 `f6d7e2280d05706643d46ae7786bd3fad6d912e4893781c3f62c73deebf38459` Source locator `/table/rows/26` |  |  |  |  |  |  |  |
| [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 26.04% | 95% CI 17.26–34.82% | 11 / 30 | 0.19usd per problem | — | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 26.04 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.19 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 17.26–34.82% confidenceInterval95 8.78 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label Gemini 3.6 Flash Source version apex--apex_2025 Observed 2026-10-21T16:52:38.728Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/11` |  |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,301elo | — | 19 / 123 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1301 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 88549 battles 15721 losses 7015 standardError Not reported winRate 55.4 wins 8706 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/20` |  |  |  |  |  |  |  |
| [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,199elo | SE ±8.74 | 17 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1199 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±8.74 averageGenerationTimeMs Not reported battles 1744 losses 869 standardError 8.7418 winRate 50.2 wins 875 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/21` |  |  |  |  |  |  |  |
| [DesignArena Native Android development](https://benchize.com/benchmarks/designarena%3Aandroid.md) | 1,209elo | — | 8 / 23 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=android) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1209 \| elo \| android \| Higher is better \| ### Configuration arenaType agents category nativeapps inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 2305 losses 1071 standardError Not reported winRate 53.5 wins 1234 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=android) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:03.000Z Evidence SHA-256 `d9d0cd4bea54b696c28f907a98ba42ebf8dd4da9da201b6c70c95f76de35f525` Source locator `/data/10` |  |  |  |  |  |  |  |
| [Kangaroo 2025 1-2](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_1-2.md) | 83.33% | 95% CI 72.79–93.87% | 6 / 16 | 0.04usd per problem | — | [matharena · kangaroo--kangaroo_2025_1-2](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.043 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_1-2 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 72.79–93.87% confidenceInterval95 10.54 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_1-2 Observed 2026-10-21T16:52:31.513Z Evidence SHA-256 `a59a4c362e2d87350330706a01dd330e9a1ac7cc64a4de0bacbf1a439d8fcf90` Source locator `/table/rows/6` |  |  |  |  |  |  |  |
| [BrokenArXiv 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--april.md) | 15.98% | 95% CI 9.48–22.48% | 14 / 17 | 0.15usd per problem | — | [matharena · arxiv_false--april](https://matharena.ai/competition_tables/arxiv_false--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 15.98 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.15 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--april predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 9.48–22.48% confidenceInterval95 6.50 problems 61 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--april) Source matharena Original model label Gemini 3.6 Flash Source version arxiv_false--april Observed 2026-10-21T16:52:24.402Z Evidence SHA-256 `e543f14dac0ba9663e8104a87738726c9848b89171a53fdca89b7baa4a892399` Source locator `/table/rows/15` |  |  |  |  |  |  |  |
| [DesignArena Video to website](https://benchize.com/benchmarks/designarena%3Avideo-to-website.md) | 1,193elo | — | 6 / 10 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=video-to-website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1193 \| elo \| video-to-website \| Higher is better \| ### Configuration arenaType models category website inputModality video sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 119047 battles 2813 losses 1417 standardError Not reported winRate 49.6 wins 1396 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=video-to-website) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:59.851Z Evidence SHA-256 `7497b4e107891bf38ad81750242b1b15b51d10f2bfc19781d85918d8f98cbbcb` Source locator `/data/6` |  |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,603.5elo | — | 39 / 90 | — | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1603.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.22 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gemini-3.6-flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gemini-3.6-flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/47` |  |  |  |  |  |  |  |
| [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 96.67% | 95% CI 92.13–101.21% | 6 / 21 | 0.08usd per problem | — | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.082 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 92.13–101.21% confidenceInterval95 4.54 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label Gemini 3.6 Flash Source version aime--aime_2026 Observed 2026-10-21T16:52:37.816Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/9` |  |  |  |  |  |  |  |
| [OpenVibeEval Accessibility](https://benchize.com/benchmarks/openvibeeval%3Aaccessibility.md) | 78 | — | 7 / 26 | — | — | [openvibeeval](https://openvibeeval.com/leaderboard/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `adjusted_score` \| 78 \| score \| sample_size_adjusted_accessibility \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.6 Flash thinkingEnabled Not reported ### Reported statistics runCount 8 ### Source [Original source](https://openvibeeval.com/leaderboard/) Source openvibeeval Original model label Gemini 3.6 Flash Evaluated 2026-08-04 Observed 2026-10-21T16:32:04.885Z Evidence SHA-256 `9b2e7d6060910e3dc7083a6a7f67377601ce78806b2b6b7693cf8d047dd63fbb` Source locator `/rows/26` |  |  |  |  |  |  |  |
| [DesignArena Agentic presentation generation](https://benchize.com/benchmarks/designarena%3Aagentic-slides.md) | 1,146elo | SE ±12.53 | 16 / 19 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-slides) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1146 \| elo \| agentic-slides \| Higher is better \| ### Configuration arenaType agents category agon_slides inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±12.53 averageGenerationTimeMs Not reported battles 862 losses 527 standardError 12.529 winRate 38.9 wins 335 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-slides) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:03.963Z Evidence SHA-256 `b732c5aba2e357cf6034f23084d5f95f8e8882f62b8bf3ee340f0cd5cd773724` Source locator `/data/24` |  |  |  |  |  |  |  |
| [BrokenArXiv 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--may.md) | 4% | 95% CI 0.16–7.84% | 20 / 20 | 0.16usd per problem | — | [matharena · arxiv_false--may](https://matharena.ai/competition_tables/arxiv_false--may) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.16 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--may predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 0.16–7.84% confidenceInterval95 3.84 problems 50 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--may) Source matharena Original model label Gemini 3.6 Flash Source version arxiv_false--may Observed 2026-10-21T16:52:24.785Z Evidence SHA-256 `b317fca30109e8c78ed5d2b835fe227b8cfbee3b6f9cb6d7aaeadca866660969` Source locator `/table/rows/22` |  |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,289elo | — | 19 / 99 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1289 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 65498 battles 3645 losses 1739 standardError Not reported winRate 52.3 wins 1906 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/20` |  |  |  |  |  |  |  |
| [Kangaroo 2025 5-6](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_5-6.md) | 88.33% | 95% CI 80.21–96.45% | 3 / 16 | 0.05usd per problem | — | [matharena · kangaroo--kangaroo_2025_5-6](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.33 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.050 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_5-6 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 80.21–96.45% confidenceInterval95 8.12 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_5-6 Observed 2026-10-21T16:52:32.526Z Evidence SHA-256 `9460cafccce0b6f3ba1f90e1090be31d6cf94dd10b9157819abc97efe624b126` Source locator `/table/rows/2` |  |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,281elo | — | 8 / 65 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1281 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 59149 battles 354 losses 151 standardError Not reported winRate 57.3 wins 203 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/7` |  |  |  |  |  |  |  |
| [ArXivMath 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--may.md) | 54.17% | 95% CI 45.25–63.09% | 15 / 21 | 0.18usd per problem | — | [matharena · arxiv--may](https://matharena.ai/competition_tables/arxiv--may) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.18 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--may predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 45.25–63.09% confidenceInterval95 8.92 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--may) Source matharena Original model label Gemini 3.6 Flash Source version arxiv--may Observed 2026-10-21T16:52:29.369Z Evidence SHA-256 `758e1bba77e36f4ced2a51b4bc0d46bd956ed94ef6f57e93e1a974b75e76a4ce` Source locator `/table/rows/17` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,197elo | SE ±6.93 | 23 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1197 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±6.93 averageGenerationTimeMs Not reported battles 2871 losses 1561 standardError 6.9287 winRate 45.6 wins 1310 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/28` |  |  |  |  |  |  |  |
| [HMMT Feb 2026](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2026.md) | 89.39% | 95% CI 81.96–96.82% | 12 / 21 | 0.1usd per problem | — | [matharena · hmmt--hmmt_feb_2026](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.39 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.10 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2026 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 81.96–96.82% confidenceInterval95 7.43 problems 33 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) Source matharena Original model label Gemini 3.6 Flash Source version hmmt--hmmt_feb_2026 Observed 2026-10-21T16:52:38.351Z Evidence SHA-256 `0dce922c33a54d29d4a1872a42d74077b491915c80d8433f4b379ea0b78bb979` Source locator `/table/rows/14` |  |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,290elo | SE ±2.13 | 22 / 116 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1290 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±2.13 averageGenerationTimeMs 78488 battles 32699 losses 15251 standardError 2.1309 winRate 53.4 wins 17448 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/26` |  |  |  |  |  |  |  |
| [Kangaroo 2025 7-8](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_7-8.md) | 90% | 95% CI 82.41–97.59% | 6 / 15 | 0.05usd per problem | — | [matharena · kangaroo--kangaroo_2025_7-8](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.046 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_7-8 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 82.41–97.59% confidenceInterval95 7.59 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_7-8 Observed 2026-10-21T16:52:33.033Z Evidence SHA-256 `197887eb5244aa6bce3570bd9eb25bbb0bb6ec95568339536d94e2859f0ee8c1` Source locator `/table/rows/7` |  |  |  |  |  |  |  |
| [DesignArena Image to HTML](https://benchize.com/benchmarks/designarena%3Aimage-to-html.md) | 1,207elo | — | 21 / 35 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-html) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1207 \| elo \| image-to-html \| Higher is better \| ### Configuration arenaType models category website inputModality image sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 94145 battles 3509 losses 1697 standardError Not reported winRate 51.6 wins 1812 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-html) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:37:58.959Z Evidence SHA-256 `94f97ebbdd53a8c56f138b620e59b3a9b35c66c3954dcaaa1b2ed4c71518b404` Source locator `/data/23` |  |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--visual_math.md) | 87.85% | 95% CI 84.4–91.3% | 5 / 15 | 0.04usd per problem | — | [matharena · overall--visual_math](https://matharena.ai/competition_tables/overall--visual_math) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.85 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.042 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--visual_math predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 84.4–91.3% confidenceInterval95 3.45 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--visual_math) Source matharena Original model label Gemini 3.6 Flash Source version overall--visual_math Observed 2026-10-21T16:52:30.998Z Evidence SHA-256 `b38d1f465012aab8b7d0930aea897d4e5be10ec02c16643c24c9251c8febb173` Source locator `/table/rows/5` |  |  |  |  |  |  |  |
| [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 71.28% | 95% CI 64.81–77.75% | 12 / 24 | 0.19usd per problem | — | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.28 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.19 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 64.81–77.75% confidenceInterval95 6.47 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label Gemini 3.6 Flash Source version apex--shortlist_2025 Observed 2026-10-21T16:52:39.300Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/13` |  |  |  |  |  |  |  |
| [ArXivMath 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--april.md) | 52.5% | 95% CI 43.57–61.43% | 11 / 19 | 0.17usd per problem | — | [matharena · arxiv--april](https://matharena.ai/competition_tables/arxiv--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.17 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--april predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 43.57–61.43% confidenceInterval95 8.93 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--april) Source matharena Original model label Gemini 3.6 Flash Source version arxiv--april Observed 2026-10-21T16:52:28.840Z Evidence SHA-256 `5139c835884bfab38f18d23a248814af4680927310bc5cd2a86ea2eab779e0a7` Source locator `/table/rows/13` |  |  |  |  |  |  |  |
| [Kangaroo 2025 11-12](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12.md) | 96.67% | 95% CI 92.13–101.21% | 5 / 16 | 0.03usd per problem | — | [matharena · kangaroo--kangaroo_2025_11-12](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.033 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 92.13–101.21% confidenceInterval95 4.54 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label Gemini 3.6 Flash Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-21T16:52:34.045Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/6` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / swebench](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aswebench.md) | 77.45% | SE ±4.14 pp | 10 / 20 | $1.38 | 1,340.98source 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` \| 77.451 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.380993 \| USD \| per_test \| Lower is better \| \| `latency` \| 1340.979 \| 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: ±4.14 pp sourcePopulation 33 stderr 4.138 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-3.6-flash Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/swebench/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,263elo | — | 29 / 117 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1263 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics averageGenerationTimeMs 80649 battles 5680 losses 2786 standardError Not reported winRate 51 wins 2894 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/40` |  |  |  |  |  |  |  |
| [ArXivMath 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--june.md) | 56.94% | 95% CI 48.85–65.03% | 17 / 22 | 0.19usd per problem | — | [matharena · arxiv--june](https://matharena.ai/competition_tables/arxiv--june) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.94 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.19 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--june predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 48.85–65.03% confidenceInterval95 8.09 problems 48 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--june) Source matharena Original model label Gemini 3.6 Flash Source version arxiv--june Observed 2026-10-21T16:52:29.905Z Evidence SHA-256 `6832faff9be7e16a6c646c59017e30a2caedebe8cf02caf617a5ed9d8fb03bab` Source locator `/table/rows/23` |  |  |  |  |  |  |  |
| [DesignArena Agentic game development](https://benchize.com/benchmarks/designarena%3Aagentic-game-dev.md) | 1,181elo | SE ±8.75 | 10 / 17 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1181 \| elo \| agentic-game-dev \| Higher is better \| ### Configuration arenaType agents category agentic_gamedev inputModality Not reported sourceModelVersion gemini-3.6-flash variationName public ### Reported statistics Uncertainty Standard error: ±8.75 averageGenerationTimeMs Not reported battles 1698 losses 889 standardError 8.7468 winRate 47.6 wins 809 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-game-dev) Source designarena Original model label Gemini 3.6 Flash Source version public Observed 2026-10-21T16:38:01.564Z Evidence SHA-256 `2bb291527289cec897df421c3c59427ce53230a312bf61790ba7ac6ca436bb4b` Source locator `/data/13` |  |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--final_answer_comps.md) | 70.84% | 95% CI 67.35–74.33% | 11 / 20 | 0.14usd per problem | — | [matharena · overall--final_answer_comps](https://matharena.ai/competition_tables/overall--final_answer_comps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.84 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--final_answer_comps predicted false sourceModelName Gemini 3.6 Flash sourceModelVersion gemini/gemini-36-flash ### Reported statistics Uncertainty 95% confidence interval: 67.35–74.33% confidenceInterval95 3.49 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--final_answer_comps) Source matharena Original model label Gemini 3.6 Flash Source version overall--final_answer_comps Observed 2026-10-21T16:52:34.395Z Evidence SHA-256 `8b08b20c1ac5aec9a829d234469bc39d40b0eb189790d84b7264c2756ffa161e` Source locator `/table/rows/12` |  |  |  |  |  |  |  |

---
Cite as: Gemini 3.6 Flash — Benchize, https://benchize.com/models/gemini-3-6-flash (retrieved 2026-10-21)