SI Index Data as of Oct 8, 2026

GPT-5.6 Terra: Price, Context, Benchmarks, and Release Details

OpenAI provisional listing · first seen Oct 8, 2026 · score computed Oct 8, 2026, 22:13 UTC
68.2
SI Score (method si-v2-absolute-shrinkage-1)
#19 of 115 ranked
100% confidence 100 percent, Full confidence — 6 of 7 expected sources in
Coverage 87% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 59.1
Math (weight 15 percent) 85.1
Preference (weight 15 percent) 77.4
Reasoning (weight 30 percent) 76.3

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
1.1Mmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Released
Jul 9, 2026models.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, pdfmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗

Benchmark results

55 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 95.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		95.8 reasoning
arc agi v1 public eval 70.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		70.8 reasoning
arc agi v1 public eval 98.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		98.3 reasoning
arc agi v1 public eval 84.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		84.8 reasoning
arc agi v1 public eval 95.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		95.6 reasoning
arc agi v1 semi private 92%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		92.0 reasoning
arc agi v1 semi private 60.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		60.2 reasoning
arc agi v1 semi private 96.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		96.5 reasoning
arc agi v1 semi private 77%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		77.0 reasoning
arc agi v1 semi private 94%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		94.0 reasoning
arc agi v2 public eval 73.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		73.9 reasoning
arc agi v2 public eval 14.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		14.9 reasoning
arc agi v2 public eval 91.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		91.3 reasoning
arc agi v2 public eval 38.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		38.9 reasoning
arc agi v2 public eval 82.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		82.6 reasoning
arc agi v2 semi private 67.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		67.1 reasoning
arc agi v2 semi private 18.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		18.8 reasoning
arc agi v2 semi private 83.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		83.9 reasoning
arc agi v2 semi private 37.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		37.5 reasoning
arc agi v2 semi private 74.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		74.2 reasoning
arc agi v3 semi private 0.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.5 reasoning
arc agi v3 semi private 0.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.0 reasoning
arc agi v3 semi private 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] openai-gpt-5-6-terra-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.8 reasoning
arc agi v3 semi private 0.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.1 reasoning
arc agi v3 semi private 0.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] openai-gpt-5-6-terra-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.7 reasoning
frontiermath tier 4 v2 70.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		70.7 math
frontiermath tiers 1 3 v2 86.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		86.0 math
frontiermath vv2 tier 1 3 84.9%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Tier 1-3; v2Published Jul 9, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		84.9 math
gpqa diamond 87.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		87.4 reasoning
gpqa diamond 93.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		93.3 reasoning
gpqa diamond 77.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		77.3 reasoning
gpqa diamond 92.9%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jul 9, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		92.9 reasoning
livebench coding code completion 2026_06_25 80.4%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 ↗ 		80.4 coding
livebench coding code generation 2026_06_25 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		76.1 coding
livebench coding javascript 2026_06_25 68.2%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 ↗ 		68.2 coding
livebench coding python 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 typescript 2026_06_25 46.7%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 ↗ 		46.7 coding
livebench math amps hard 2026_06_25 98%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 ↗ 		98.0 math
livebench math integrals with game 2026_06_25 95%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 ↗ 		95.0 math
livebench math math comp 2026_06_25 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		95.1 math
livebench math olympiad 2026_06_25 91.5%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 ↗ 		91.5 math
livebench math simplify 2026_06_25 61.4%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 ↗ 		61.4 math
livebench reasoning connections 2026_06_25 93%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 ↗ 		93.0 reasoning
livebench reasoning consecutive events 2026_06_25 87.7%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 ↗ 		87.7 reasoning
livebench reasoning logic with navigation 2026_06_25 76%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 ↗ 		76.0 reasoning
livebench reasoning spatial 2026_06_25 100%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 ↗ 		100.0 reasoning
livebench reasoning theory of mind 2026_06_25 86.5%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 ↗ 		86.5 reasoning
livebench reasoning zebra puzzle 2026_06_25 100%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 ↗ 		100.0 reasoning
lmarena text 1446.3 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 8, 2026 · CC-BY-4.0
Open source ↗ 		77.4 preference
otis mock aime 2024 2025 88.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Aug 7, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		88.9 math
otis mock aime 2024 2025 99.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jul 9, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		99.7 math
otis mock aime 2024 2025 53.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 7, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		53.3 math
swe bench pro 63.4%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jul 9, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		63.4 coding
terminal bench v2 1 87.4%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] 2.1Published Jul 9, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		87.4 coding
terminal bench v4 0 21.5%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; maxPublished Sep 3, 2026 Retrieved Oct 8, 2026 · Apache-2.0; factual citation
Open source ↗ 		21.5 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 (6)

  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · 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
  • Terminal-Bench · arrived Oct 8, 2026

pending Awaiting (1)

  • Humanity’s Last Exam · carries 13% 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.