SI Index Data as of Oct 8, 2026

GPT-6 Sol: Price, Context, Benchmarks, and Release Details

OpenAI · first seen Oct 8, 2026 · score computed Oct 8, 2026, 22:13 UTC
68.9
SI Score (method si-v2-absolute-shrinkage-1)
#15 of 115 ranked
100% confidence 100 percent, Full confidence — 5 of 7 expected sources in
Coverage 83% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 61.9
Math (weight 15 percent) 91.3
Preference (weight 15 percent) 72.7
Reasoning (weight 30 percent) 78.1

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
Sep 22, 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, image, pdfmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗

Benchmark results

47 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 91.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		91.4 reasoning
arc agi v1 public eval 79.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		79.3 reasoning
arc agi v1 public eval 97.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-sol-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		97.8 reasoning
arc agi v1 public eval 88.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		88.9 reasoning
arc agi v1 public eval 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. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		96.5 reasoning
arc agi v1 semi private 91%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		91.0 reasoning
arc agi v1 semi private 72.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		72.2 reasoning
arc agi v1 semi private 95.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-sol-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		95.5 reasoning
arc agi v1 semi private 83.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		83.7 reasoning
arc agi v1 semi private 92.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		92.7 reasoning
arc agi v2 public eval 63.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		63.6 reasoning
arc agi v2 public eval 25.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		25.6 reasoning
arc agi v2 public eval 90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-sol-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		90.0 reasoning
arc agi v2 public eval 49.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		49.4 reasoning
arc agi v2 public eval 81.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		81.8 reasoning
arc agi v2 semi private 68.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		68.9 reasoning
arc agi v2 semi private 31.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		31.5 reasoning
arc agi v2 semi private 89.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-sol-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		89.6 reasoning
arc agi v2 semi private 57.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		57.8 reasoning
arc agi v2 semi private 78.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		78.1 reasoning
arc agi v3 semi private 0.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.9 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. Evaluation conducted with 'low' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.1 reasoning
arc agi v3 semi private 4.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort using the standard harness. [variant] openai-gpt-6-sol-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		4.6 reasoning
arc agi v3 semi private 0.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'medium' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-mediumPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.4 reasoning
arc agi v3 semi private 1.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'xhigh' reasoning effort using the standard harness. Partial dataset coverage: scores use full catalog denominators; costs include recorded usage only, excluding unrecorded attempts. [variant] openai-gpt-6-sol-xhighPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		1.8 reasoning
frontiermath tier 4 v2 90%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		90.0 math
frontiermath tiers 1 3 v2 89.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		89.8 math
gpqa diamond 94.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		94.3 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 83.1%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 ↗ 		83.1 coding
livebench coding javascript 2026_06_25 63.6%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 ↗ 		63.6 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 40%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 ↗ 		40.0 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 99%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 math
livebench math math comp 2026_06_25 97.1%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 ↗ 		97.1 math
livebench math olympiad 2026_06_25 91.4%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 ↗ 		91.4 math
livebench math simplify 2026_06_25 69.3%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 ↗ 		69.3 math
livebench reasoning connections 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 consecutive events 2026_06_25 89.5%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 ↗ 		89.5 reasoning
livebench reasoning logic with navigation 2026_06_25 74%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 ↗ 		74.0 reasoning
livebench reasoning spatial 2026_06_25 96%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 ↗ 		96.0 reasoning
livebench reasoning theory of mind 2026_06_25 84.6%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 ↗ 		84.6 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 1395.4 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 8, 2026 · CC-BY-4.0
Open source ↗ 		72.7 preference
otis mock aime 2024 2025 100%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Sep 22, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		100.0 math
terminal bench v4 0 49.4%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Codex; maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · Apache-2.0; factual citation
Open source ↗ 		49.4 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 (5)

  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • LiveBench · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026
  • Terminal-Bench · arrived Oct 8, 2026

pending Awaiting (2)

  • Humanity’s Last Exam · carries 13% of expected weight
  • Official model cards via models.dev · carries 4% 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.