OpenAI, released Dec 11, 2025

GPT-5.2price, context, benchmarks and release details

100% confidence 100 percent, Full confidence, 8 of 9 expected sources in
65.9
SI Score
#33 of 142 ranked models
Input, per 1M tokens
$1.75models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.2 Retrieved Oct 9, 2026 · MIT
Open source ↗
Output, per 1M tokens
$14.00models.devFirst-party hosted API; MIT models.dev transcription. Provider documentation: https://platform.openai.com/docs/models. Exact canonical endpoint; lowest short-context Standard USD token tier; cache/batch discounts excluded. Deprecated endpoints excluded; openai/gpt-5.2 Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
400Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Dec 11, 2025OpenAI API changelogPublished source fact Retrieved Oct 9, 2026 · factual citation
Open source ↗

How the score breaks down

Coding (weight 40 percent) 60.1
Math (weight 15 percent) 75.8
Preference (weight 15 percent) 74.3
Reasoning (weight 30 percent) 67.4

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. 31 DeepSeek V4.1 Flash 66.2
  2. 32 Kimi K2 Thinking Turbo 66.1
  3. 33 GPT-5.2 65.9
  4. 34 GLM-5.2 65.7
  5. 35 Gemini 3.6 Flash 65.5

Full leaderboard

Benchmark results

28 benchmarks, 56 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 95%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 95.0 5 settings
  • Setting 1 90.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 65.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 80.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 16.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-nonePublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 5 95%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (public eval)
ARC-AGI-1 (semi-private)reasoning 86.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 86.2 5 settings
  • Setting 1 78.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 55.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 72.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 12.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-nonePublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 5 86.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (semi-private)
ARC-AGI-2 (public eval)reasoning 59.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 59.8 5 settings
  • Setting 1 39.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 8.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 27.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 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. [variant] gpt-5-2-2025-12-11-thinking-nonePublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 5 59.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (public eval)
ARC-AGI-2 (semi-private)reasoning 52.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 52.9 5 settings
  • Setting 1 43.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 9.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 26.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 0.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-nonePublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 5 52.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2-2025-12-11-thinking-xhighPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (semi-private)
GPQA Diamondreasoning 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Dec 13, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 91.4 5 settings
  • no reasoning 73.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 82.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 87.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 88.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • xhigh effort 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Dec 13, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About GPQA Diamond
Humanity's Last Exam (Scale AI)reasoning 27.8%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 Dec 15, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 27.8
LiveBench Reasoning: connectionsreasoning 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
LiveBench Reasoning: consecutive eventsreasoning 88.9%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 ↗ 88.9
LiveBench Reasoning: logic with navigationreasoning 74%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 ↗ 74.0
LiveBench Reasoning: spatialreasoning 96%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 ↗ 96.0
LiveBench Reasoning: theory of mindreasoning 78.8%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 ↗ 78.8
LiveBench Reasoning: zebra puzzlesreasoning 84%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 ↗ 84.0
FrontierMath Tier 4 (v2)math 31.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Jun 11, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 31.7
FrontierMath Tiers 1–3 (v2)math 67.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Jun 11, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 67.4
LiveBench Math: AMPS Hardmath 97%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 ↗ 97.0
LiveBench Math: competition mathmath 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
LiveBench Math: integralsmath 92%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 ↗ 92.0
LiveBench Math: olympiadmath 88.6%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 ↗ 88.6
LiveBench Math: simplifymath 54.1%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 ↗ 54.1
OTIS Mock AIME 2024–2025math 96.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 96.1 5 settings
  • no reasoning 62.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 78.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 93.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 96.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Dec 11, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • xhigh effort 96.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Dec 13, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
LiveBench Coding: code completioncoding 76.1%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 ↗ 76.1
LiveBench Coding: code generationcoding 76.1%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 ↗ 76.1
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 55%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 ↗ 55.0
LiveBench Coding: TypeScriptcoding 36.7%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 ↗ 36.7
SWE-bench Pro (public)coding 29.9%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 ↗ 29.9 2 settings
  • Setting 1 29.9%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 ↗
  • Setting 2 29.9%SWE-bench Pro (public)Published steward score [variant] Published Jan 27, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About SWE-bench Pro (public)
SWE-bench Verifiedcoding 73.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Feb 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 73.8 4 settings
  • high effort 73.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Feb 12, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 69%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 1.17.2Published Dec 11, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 71.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; high; 1.17.2Published Dec 11, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 72.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; high; 2.0.0Published Feb 17, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About SWE-bench Verified
LMArena Textpreference 1412.2 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 74.3

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, imagemodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
95% of expected source weight

Reported (8)

  • 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
  • SWE-bench VerifiedOct 8, 2026
  • SWE-bench Pro (public)Oct 8, 2026

Awaiting (1)

  • Terminal-Bench5% 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