OpenAI, released Aug 7, 2025

GPT-5price, context, benchmarks and release details

100% confidence 100 percent, Full confidence, 8 of 10 expected sources in
55.7
SI Score
#83 of 142 ranked models
Input, per 1M tokens
$1.25models.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 Retrieved Oct 9, 2026 · MIT
Open source ↗
Output, per 1M tokens
$10.00models.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 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
Aug 7, 2025OpenAI API changelogPublished source fact Retrieved Oct 9, 2026 · factual citation
Open source ↗

How the score breaks down

Coding (weight 40 percent) 66.7
Math (weight 15 percent) 55.6
Preference (weight 15 percent) 73.7
Reasoning (weight 30 percent) 35.2

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, 06:15 UTC.

Around it on the leaderboard

  1. 81 MiMo-V2.6-Flash 55.8
  2. 82 DeepSeek V3 0324 55.7
  3. 83 GPT-5 55.7
  4. 84 MiniMax-M2 55.7
  5. 85 GPT-5.1 55.7

Full leaderboard

Benchmark results

14 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 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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 65.9 3 settings
  • Setting 1 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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 48.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 63.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (public eval)
ARC-AGI-1 (semi-private)reasoning 65.7%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 65.7 3 settings
  • Setting 1 65.7%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 44%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 56.2%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-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (semi-private)
ARC-AGI-2 (public eval)reasoning 9.6%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 9.6 3 settings
  • Setting 1 9.6%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 2.5%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 7.6%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-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (public eval)
ARC-AGI-2 (semi-private)reasoning 9.9%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 9.9 3 settings
  • Setting 1 9.9%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 1.9%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 7.5%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-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (semi-private)
GPQA Diamondreasoning 86.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 86.2 3 settings
  • minimal effort 71.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 20, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 85.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 86.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About GPQA Diamond
Humanity's Last Exam (Scale AI)reasoning 25.3%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. Sampled at reasoning_effort: 'high'. [variant] Published Aug 7, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 25.3
FrontierMath Tier 4 (v2)math 22.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 11, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 22.0
FrontierMath Tiers 1–3 (v2)math 55.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 55.4 3 settings
  • minimal effort 18.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • low effort 37.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 55.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 10, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tiers 1–3 (v2)
MATH Level 5math 98.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 98.1 2 settings
  • medium effort 97.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 20, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 98.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About MATH Level 5
OTIS Mock AIME 2024–2025math 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 91.4 3 settings
  • minimal effort 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 20, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 87.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
Aider Polyglotcoding 81.3%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Aug 25, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 81.3
SWE-bench Pro (public)coding 41.8%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 ↗ 41.8 2 settings
  • Setting 1 41.8%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 41.8%SWE-bench Pro (public)Published steward score [variant] Published Nov 26, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About SWE-bench Pro (public)
SWE-bench Verifiedcoding 74.4%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Prometheus-v1.2.1Published Oct 15, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 74.4 6 settings
  • medium effort 71.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Feb 5, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 73.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Feb 6, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 3 65%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; medium; 1.7.0Published Aug 7, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 4 71.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] OpenHandsPublished Aug 7, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 5 71.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Prometheus-v1.2Published Sep 29, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 6 74.4%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Prometheus-v1.2.1Published Oct 15, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About SWE-bench Verified
LMArena Textpreference 1406.2 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 73.7

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
86% of expected source weight

Reported (8)

  • Aider polyglotOct 8, 2026
  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • Humanity’s Last ExamOct 8, 2026
  • Official model cards via models.devOct 8, 2026
  • LMArena / ArenaOct 8, 2026
  • SWE-bench VerifiedOct 8, 2026
  • SWE-bench Pro (public)Oct 8, 2026

Awaiting (2)

  • LiveBench10% of weight
  • 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