SI Index Data as of Oct 9, 2026

Gemini 3.8 Flash: Price, Context, Benchmarks, and Release Details

Google · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:47 UTC
68.8
SI Score (method si-v3-retained-evidence-2)
#17 of 140 ranked
100% confidence 100 percent, Full confidence — 7 of 7 expected sources in
Coverage 100% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 56.4
Math (weight 15 percent) 77.5
Preference (weight 15 percent) 81.5
Reasoning (weight 30 percent) 74.5

Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.

Facts

Input price / 1M
$0.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation
Open source ↗
Output price / 1M
$3.75Google Gemini pricingOfficial paid Standard text rate, lowest short-context tier; current promotional price if dated; excludes free/Batch/Flex/audio Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation
Open source ↗
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
65.5Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Sep 2, 2026Google Gemini release notesPublished source fact Retrieved Oct 9, 2026 · CC-BY-4.0 factual citation
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, video, audio, pdfmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

41 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 98%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] google-gemini-3-8-flash-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		98.0 reasoning
arc agi v1 public eval 94.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		94.5 reasoning
arc agi v1 public eval 97.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		97.8 reasoning
arc agi v1 semi private 98.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] google-gemini-3-8-flash-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		98.5 reasoning
arc agi v1 semi private 90.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		90.5 reasoning
arc agi v1 semi private 97.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		97.5 reasoning
arc agi v2 public eval 92.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] google-gemini-3-8-flash-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		92.5 reasoning
arc agi v2 public eval 77.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		77.2 reasoning
arc agi v2 public eval 87.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		87.5 reasoning
arc agi v2 semi private 89.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] google-gemini-3-8-flash-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		89.2 reasoning
arc agi v2 semi private 77.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		77.5 reasoning
arc agi v2 semi private 82.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		82.9 reasoning
arc agi v3 semi private 10.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] google-gemini-3-8-flash-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		10.4 reasoning
arc agi v3 semi private 6.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		6.0 reasoning
arc agi v3 semi private 4.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. [variant] google-gemini-3-8-flash-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.0 reasoning
frontiermath tier 4 v2 22.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Sep 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		22.0 math
frontiermath tiers 1 3 v2 68.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Sep 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		68.4 math
gpqa diamond 95.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Sep 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.4 reasoning
hle 1811 verified and revised items 54.9%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] 1811 verified and revised items Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		54.9 reasoning
hle scale 44.5%Humanity’s Last ExamPotential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. [variant] Published Sep 9, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		44.5 reasoning
livebench coding code completion 2026_06_25 71.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		71.7 coding
livebench coding code generation 2026_06_25 73.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		73.2 coding
livebench coding javascript 2026_06_25 72.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		72.7 coding
livebench coding python 2026_06_25 50%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		50.0 coding
livebench coding typescript 2026_06_25 40%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		40.0 coding
livebench math amps hard 2026_06_25 99%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		99.0 math
livebench math integrals with game 2026_06_25 80%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		80.0 math
livebench math math comp 2026_06_25 95.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		95.1 math
livebench math olympiad 2026_06_25 92.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		92.2 math
livebench math simplify 2026_06_25 75.4%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		75.4 math
livebench reasoning connections 2026_06_25 100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		100.0 reasoning
livebench reasoning consecutive events 2026_06_25 20.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		20.6 reasoning
livebench reasoning logic with navigation 2026_06_25 82%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		82.0 reasoning
livebench reasoning spatial 2026_06_25 100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		100.0 reasoning
livebench reasoning theory of mind 2026_06_25 76.9%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		76.9 reasoning
livebench reasoning zebra puzzle 2026_06_25 98.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		98.3 reasoning
lmarena text 1497.0 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		81.5 preference
otis mock aime 2024 2025 98.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Sep 2, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.9 math
terminal bench v2 1 89.4%Official model cards via models.devLab-reported; metric pass@1; transcribed by MIT models.dev catalog; not independently evaluated [variant] Terminus 2; 2.1 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		89.4 coding
terminal bench v4 0 19.1%Official model cards via models.devLab-reported; metric pass@1; transcribed by MIT models.dev catalog; not independently evaluated [variant] 4.0 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		19.1 coding
terminal bench v4 0 19.1%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] mini-SWE-agent; highPublished Sep 3, 2026 Retrieved Oct 9, 2026 · Apache-2.0; factual citation
Open source ↗ 		19.1 coding

Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.

Sources: in and pending

in Reported (7)

  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Humanity’s Last Exam · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LiveBench · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026
  • Terminal-Bench · arrived Oct 8, 2026

pending Awaiting (0)

Every expected source has reported for this model.

The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.