Google, released Feb 19, 2026

Gemini 3.1 Pro Previewprice, context, benchmarks and release details

Provisional: not enough results to rank yet 100% confidence 100 percent, Full confidence, 6 of 7 expected sources in
68.1
SI Score
#22 of 142 ranked models
Input, per 1M tokens
$2.00Google 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, per 1M tokens
$12.00Google 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
Feb 19, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

How the score breaks down

Coding (weight 40 percent) 57.0
Math (weight 15 percent) 75.9
Preference (weight 15 percent) 80.3
Reasoning (weight 30 percent) 77.1

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

  1. 20 Claude Sonnet 4.6 68.3
  2. 21 GPT-5.6 Terra 68.2
  3. 22 Gemini 3.1 Pro Preview 68.1
  4. 23 MiniMax-M3 68.0
  5. 24 GLM-5.3 67.7

Full leaderboard

Benchmark results

32 benchmarks, 35 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

ARC-AGI-1 (public eval)reasoning 97.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gemini-3-1-pro-previewPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 97.2
ARC-AGI-1 (semi-private)reasoning 98%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gemini-3-1-pro-previewPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 98.0
ARC-AGI-2reasoning 77.1%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published May 19, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 77.1
ARC-AGI-2 (public eval)reasoning 88.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gemini-3-1-pro-previewPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 88.1
ARC-AGI-2 (semi-private)reasoning 77.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gemini-3-1-pro-previewPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 77.1
ARC-AGI-3 (semi-private)reasoning 0.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] google-gemini-3-1-pro-previewPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 0.4
GPQA Diamondreasoning 94.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 94.4 3 settings
  • high effort 94.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 94.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 3 94.3%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Apr 23, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
    Open source ↗
About GPQA Diamond
Humanity's Last Exam (full set, text + multimodal)reasoning 44.4%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] full set, text + MMPublished May 19, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 44.4
Humanity's Last Exam (Scale AI)reasoning 46.4%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 Apr 10, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 46.4
LiveBench Reasoning: connectionsreasoning 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
LiveBench Reasoning: consecutive eventsreasoning 85.2%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 ↗ 85.2
LiveBench Reasoning: logic with navigationreasoning 72%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 ↗ 72.0
LiveBench Reasoning: spatialreasoning 98%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 ↗ 98.0
LiveBench Reasoning: theory of mindreasoning 80.8%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 ↗ 80.8
LiveBench Reasoning: zebra puzzlesreasoning 85.3%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 ↗ 85.3
FrontierMath Tier 4 (v2)math 26.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jun 11, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 26.8
FrontierMath Tiers 1–3 (v2)math 59.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jun 11, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 59.6
LiveBench Math: AMPS Hardmath 98%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 ↗ 98.0
LiveBench Math: competition mathmath 96.1%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 ↗ 96.1
LiveBench Math: integralsmath 78%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 ↗ 78.0
LiveBench Math: olympiadmath 92.1%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 ↗ 92.1
LiveBench Math: simplifymath 71.0%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 ↗ 71.0
OTIS Mock AIME 2024–2025math 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 95.6 2 settings
  • high effort 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
LiveBench Coding: code completioncoding 78.3%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 ↗ 78.3
LiveBench Coding: code generationcoding 74.6%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 ↗ 74.6
LiveBench Coding: JavaScriptcoding 59.1%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 ↗ 59.1
LiveBench Coding: Pythoncoding 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
LiveBench Coding: TypeScriptcoding 23.3%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 ↗ 23.3
SWE-bench Procoding 54.2%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published May 28, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 54.2
SWE-bench Pro (public)coding 46.1%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] public Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 46.1
Terminal-Bench 2.1coding 70.3%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Terminus-2; 2.1Published May 28, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 70.3
LMArena Textpreference 1480.5 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 80.3

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

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 ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
94% of expected source weight

Reported (6)

  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • Humanity’s Last ExamOct 8, 2026
  • Official model cards via models.devOct 8, 2026
  • LiveBenchOct 8, 2026
  • LMArena / ArenaOct 8, 2026

Awaiting (1)

  • Terminal-Bench6% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed