OpenAI, released Apr 16, 2025

o4-miniprice, context, benchmarks and release details

Provisional: not enough results to rank yet 87% confidence 87 percent, High confidence, 5 of 9 expected sources in
51.2
SI Score
#103 of 142 ranked models
Input, per 1M tokens
$1.10LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded Retrieved Oct 9, 2026 · MIT
Open source ↗
Output, per 1M tokens
$4.40LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://developers.openai.com/api/docs/pricing. Exact endpoint only; cache/batch/long-context rates excluded Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
200Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
100Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Apr 16, 2025models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

How the score breaks down

Coding (weight 40 percent) 63.4
Math (weight 15 percent) 47.2
Preference (weight 15 percent) 68.3
Reasoning (weight 30 percent) 29.9

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. 101 Claude Sonnet 3.5 v2 51.9
  2. 102 Claude Opus 4.1 51.5
  3. 103 o4-mini 51.2
  4. 104 Llama 4 Scout 17B Instruct 51.0
  5. 105 GPT-5 Mini 50.6

Full leaderboard

Benchmark results

12 benchmarks, 27 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 68.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 68.0 3 settings
  • Setting 1 68.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 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] o4-mini-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 50.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (public eval)
ARC-AGI-1 (semi-private)reasoning 58.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 58.7 3 settings
  • Setting 1 58.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 21.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 41.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-1 (semi-private)
ARC-AGI-2 (public eval)reasoning 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] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 7.5 3 settings
  • Setting 1 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] o4-mini-2025-04-16-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] o4-mini-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 2.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (public eval)
ARC-AGI-2 (semi-private)reasoning 6.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 6.1 3 settings
  • Setting 1 6.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 1.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 3 2.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o4-mini-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About ARC-AGI-2 (semi-private)
GPQA Diamondreasoning 79.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 79.6 3 settings
  • low effort 75.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 11, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 77.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 79.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About GPQA Diamond
FrontierMath Tier 4 (v2)math 4.9%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 ↗ 4.9
FrontierMath Tiers 1–3 (v2)math 36.1%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 ↗ 36.1 3 settings
  • low effort 16.1%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 ↗
  • medium effort 28.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 36.1%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 ↗
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 Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 97.8
OTIS Mock AIME 2024–2025math 81.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 81.7 3 settings
  • low effort 57.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • medium effort 73.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • high effort 81.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Apr 16, 2025 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
About OTIS Mock AIME 2024–2025
Aider Polyglotcoding 72%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Apr 16, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 72.0
SWE-bench Verifiedcoding 64.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] PatchPilot-v1.1Published May 3, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 64.6 2 settings
  • Setting 1 45%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 1.0.0Published Jul 26, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
  • Setting 2 64.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] PatchPilot-v1.1Published May 3, 2025 Retrieved Oct 9, 2026 · factual citation
    Open source ↗
About SWE-bench Verified
LMArena Textpreference 1353.2 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 68.3

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
70% of expected source weight

Reported (5)

  • Aider polyglotOct 8, 2026
  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • LMArena / ArenaOct 8, 2026
  • SWE-bench VerifiedOct 8, 2026

Awaiting (4)

  • Humanity’s Last Exam11% of weight
  • Official model cards via models.dev4% of weight
  • LiveBench11% 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