SI Index Data as of Oct 8, 2026

GPT-5.4 mini: Price, Context, Benchmarks, and Release Details

OpenAI · first seen Oct 8, 2026 · score computed Oct 8, 2026, 22:13 UTC
55.8
SI Score (method si-v2-absolute-shrinkage-1)
#72 of 115 ranked
69% confidence 69 percent, Medium confidence — 4 of 7 expected sources in
Coverage 55% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 54.1
Math (weight 15 percent) 73.6
Preference (weight 15 percent) 74.2
Reasoning (weight 30 percent) 55.7

Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.

Facts

Input price / 1M
not yet reported
Output price / 1M
not yet reported
Context window
400Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Released
Mar 17, 2026OpenAI API changelogPublished source fact Retrieved Oct 8, 2026 · factual citation
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, imagemodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗

Benchmark results

38 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 66.3%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-5-4-mini-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		66.3 reasoning
arc agi v1 public eval 31.8%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-5-4-mini-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		31.8 reasoning
arc agi v1 public eval 55.4%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-5-4-mini-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		55.4 reasoning
arc agi v1 public eval 75.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-mini-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		75.1 reasoning
arc agi v1 semi private 58.0%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-5-4-mini-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		58.0 reasoning
arc agi v1 semi private 13%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-5-4-mini-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		13.0 reasoning
arc agi v1 semi private 40.8%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-5-4-mini-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		40.8 reasoning
arc agi v1 semi private 63.7%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-5-4-mini-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		63.7 reasoning
arc agi v2 public eval 7.0%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-5-4-mini-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		7.0 reasoning
arc agi v2 public eval 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-5-4-mini-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.8 reasoning
arc agi v2 public eval 5.4%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-5-4-mini-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		5.4 reasoning
arc agi v2 public eval 17.8%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-5-4-mini-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		17.8 reasoning
arc agi v2 semi private 13.2%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-5-4-mini-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		13.2 reasoning
arc agi v2 semi private 1.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-4-mini-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		1.1 reasoning
arc agi v2 semi private 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-5-4-mini-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		4.4 reasoning
arc agi v2 semi private 18.9%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-5-4-mini-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		18.9 reasoning
gpqa diamond 88%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhighPublished Mar 17, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		88.0 reasoning
hle 28.2%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] without toolsPublished Mar 17, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		28.2 reasoning
hle tools 41.5%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Mar 17, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		41.5 reasoning
livebench coding code completion 2026_06_25 75.6%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		75.6 coding
livebench coding code generation 2026_06_25 67.7%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		67.7 coding
livebench coding javascript 2026_06_25 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		50.0 coding
livebench coding python 2026_06_25 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		55.0 coding
livebench coding typescript 2026_06_25 20%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		20.0 coding
livebench math amps hard 2026_06_25 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		97.0 math
livebench math integrals with game 2026_06_25 37%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		37.0 math
livebench math math comp 2026_06_25 94.1%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		94.1 math
livebench math olympiad 2026_06_25 85.7%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		85.7 math
livebench math simplify 2026_06_25 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		54.1 math
livebench reasoning connections 2026_06_25 99.0%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		99.0 reasoning
livebench reasoning consecutive events 2026_06_25 63.0%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		63.0 reasoning
livebench reasoning logic with navigation 2026_06_25 60%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		60.0 reasoning
livebench reasoning spatial 2026_06_25 88%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		88.0 reasoning
livebench reasoning theory of mind 2026_06_25 76.9%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		76.9 reasoning
livebench reasoning zebra puzzle 2026_06_25 60.4%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		60.4 reasoning
lmarena text 1411.4 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 8, 2026 · CC-BY-4.0
Open source ↗ 		74.2 preference
swe bench pro 54.4%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhighPublished Mar 17, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		54.4 coding
terminal bench v2 0 60%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] reasoning effort xhigh; 2.0Published Mar 17, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		60.0 coding

Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.

Sources: in and pending

in Reported (4)

  • ARC Prize · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LiveBench · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026

pending Awaiting (3)

  • Epoch AI Benchmarking · carries 25% of expected weight
  • Humanity’s Last Exam · carries 13% of expected weight
  • Terminal-Bench · carries 6% of expected weight

The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.