OpenAI, released Aug 7, 2025

GPT-5 Miniprice, context, benchmarks and release details

99% confidence 99 percent, High confidence, 5 of 8 expected sources in
50.6
SI Score
#105 of 142 ranked models
Input, per 1M tokens
$0.25models.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-mini Retrieved Oct 9, 2026 · MIT
Open source ↗
Output, per 1M tokens
$2.00models.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-mini 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) 62.4
Math (weight 15 percent) 48.5
Preference (weight 15 percent) 70.4
Reasoning (weight 30 percent) 26.3

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. 103 o4-mini 51.2
  2. 104 Llama 4 Scout 17B Instruct 51.0
  3. 105 GPT-5 Mini 50.6
  4. 106 Qwen3 32B 50.4
  5. 107 Qwen3 235B-A22B 50.3

Full leaderboard

Benchmark results

12 benchmarks, 29 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 61.5%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 61.5 3 settings
  • Setting 1 61.5%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 24.4%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-mini-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 46.3%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-mini-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 54.3%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 54.3 3 settings
  • Setting 1 54.3%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 26.3%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-mini-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 37.3%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-mini-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 5.8%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 5.8 3 settings
  • Setting 1 5.8%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 0.3%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-mini-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 0.6%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-mini-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 4.4%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 4.4 3 settings
  • Setting 1 4.4%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-mini-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 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-mini-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 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-mini-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (semi-private)
GPQA Diamondreasoning 75%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 75.0 3 settings
  • minimal effort 71.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 71.7%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 75%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About GPQA Diamond
Humanity's Last Exam (Scale AI)reasoning 19.4%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 Aug 22, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 19.4
FrontierMath Tier 4 (v2)math 12.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 12.2
FrontierMath Tiers 1–3 (v2)math 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 46.7 3 settings
  • minimal effort 6.0%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 18.2%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 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 12, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About FrontierMath Tiers 1–3 (v2)
MATH Level 5math 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 97.8 2 settings
  • medium effort 96.8%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 97.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About MATH Level 5
OTIS Mock AIME 2024–2025math 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 86.7 3 settings
  • minimal effort 55.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 78.3%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 86.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 30, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
SWE-bench Verifiedcoding 64.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Feb 1, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 64.7 3 settings
  • medium effort 64.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Feb 1, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 56.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 2.0.0Published Feb 17, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 59.8%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 ↗
About SWE-bench Verified
LMArena Textpreference 1373.3 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 70.4

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
79% of expected source weight

Reported (5)

  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • Humanity’s Last ExamOct 8, 2026
  • LMArena / ArenaOct 8, 2026
  • SWE-bench VerifiedOct 8, 2026

Awaiting (3)

  • Official model cards via models.dev4% of weight
  • LiveBench11% of weight
  • 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