# Gemini 3.8 FlashMedium

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-3-8-flash-medium. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-3-8-flash-medium.

Google

Canonical URL: https://benchize.com/models/gemini-3-8-flash-medium
Last updated: Wed, 21 Oct 2026 18:52:20 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 |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 95.72% | — | 3 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 95.72 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.1 \| percent \| category \| Higher is better \| \| `language` \| 98.16 \| percent \| category \| Higher is better \| \| `utility` \| 99.2 \| percent \| category \| Higher is better \| \| `reasoning` \| 96.72 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.84 \| percent \| category \| Higher is better \| \| `rule_following` \| 92.86 \| percent \| category \| Higher is better \| \| `hallucination` \| 96.88 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort medium Model configuration Gemini 3.8 Flash (Reasoning, Medium) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.8 Flash (Reasoning, Medium) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/3` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 29.68% | — | 18 / 113 | $0.55 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 29.68 \| percent \| reported \| Higher is better \| \| `cost` \| 0.55 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote true Fallback policy Not reported Reasoning effort medium Model configuration Gemini 3.8 Flash (Medium) thinkingEnabled true ### Reported statistics rank 18 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Gemini 3.8 Flash (Medium) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/17` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 82.92% | — | 37 / 212 | 0.25usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.8291666666666667 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.2477876749999999 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup google-gemini-3-8-flash modelType CoT Reasoning effort medium sourceModelVersion google-gemini-3-8-flash-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Gemini 3.8 Flash (Medium) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/245` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 71.02% | Range 68.74–73.3% | 10 / 70 | $1.97 | 826.55s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.7101769911504425 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.831858407079646 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 1.9671024789823006 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 826.5496385464602 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort medium sourceConfiguration mini_swe_agent_gemini_3_8_flash_medium ### Reported statistics Uncertainty Reported interval: 68.74–73.3% interval [0.6873689454216633,0.7329850368792218] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 452 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label gemini-3-8-flash Observed 2026-10-21T16:30:23.371Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/9` |  |  |  |  |  |  |  |
| [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 3.99% | — | 19 / 53 | 2,727.66usd | — | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.039878093830617266 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 2727.66378825 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup google-gemini-3-8-flash modelType CoT Reasoning effort medium sourceModelVersion google-gemini-3-8-flash-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label Gemini 3.8 Flash (Medium) Source version v3 Observed 2026-10-21T16:34:21.112Z Evidence SHA-256 `1aaee2199f8c6d9b5a589aab2fd2480a729e9132f8cf8fbf7b49f81dbd5b2c49` Source locator `/evaluations/52` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 97.5% | — | 12 / 213 | 0.11usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.975 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.10754999250000002 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup google-gemini-3-8-flash modelType CoT Reasoning effort medium sourceModelVersion google-gemini-3-8-flash-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Gemini 3.8 Flash (Medium) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/242` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 53.45% | — | 73 / 125 | $2.21 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5345 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5962 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.2053 \| USD \| per_rollout \| Lower is better \| ### Configuration harness chisel Reasoning effort medium sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Gemini 3.8 Flash Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Gemini%203.8%20Flash/medium/extended` |  |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 41.19% | — | 65 / 125 | $2.6 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4119 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.4673 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.5954 \| USD \| per_rollout \| Lower is better \| ### Configuration harness chisel Reasoning effort medium sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Gemini 3.8 Flash Observed 2026-10-21T16:31:00.878Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Gemini%203.8%20Flash/medium/main` |  |  |  |  |  |  |  |

---
Cite as: Gemini 3.8 FlashMedium — Benchize, https://benchize.com/models/gemini-3-8-flash-medium (retrieved 2026-10-21)