SI Index Data as of Oct 9, 2026

o3: Price, Context, Benchmarks, and Release Details

OpenAI provisional listing · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:50 UTC
55.4
SI Score (method si-v3-retained-evidence-2)
#87 of 140 ranked
87% confidence 87 percent, High confidence — 5 of 9 expected sources in
Coverage 70% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 66.3
Math (weight 15 percent) 65.3
Preference (weight 15 percent) 74.1
Reasoning (weight 30 percent) 34.6

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
$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/o3 Retrieved Oct 9, 2026 · MIT
Open source ↗
Output price / 1M
$8.00models.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/o3 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 ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, pdfmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

26 results
Benchmark Raw result Normalized (0–100) Pillar
aider polyglot 76.9%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Jun 25, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 		76.9 coding
arc agi v1 public eval 64.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		64.3 reasoning
arc agi v1 public eval 47.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		47.6 reasoning
arc agi v1 public eval 56.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		56.7 reasoning
arc agi v1 semi private 60.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		60.8 reasoning
arc agi v1 semi private 41.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		41.5 reasoning
arc agi v1 semi private 53.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		53.8 reasoning
arc agi v2 public eval 2.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.9 reasoning
arc agi v2 public eval 2.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.7 reasoning
arc agi v2 public eval 4.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.5 reasoning
arc agi v2 semi private 6.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		6.5 reasoning
arc agi v2 semi private 2.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.0 reasoning
arc agi v2 semi private 3.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] o3-2025-04-16-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		3.0 reasoning
frontiermath tiers 1 3 v2 33.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		33.3 math
frontiermath tiers 1 3 v2 19.3%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 ↗ 		19.3 math
frontiermath tiers 1 3 v2 29.8%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 ↗ 		29.8 math
gpqa diamond 81.8%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 ↗ 		81.8 reasoning
gpqa diamond 79.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		79.8 reasoning
gpqa diamond 80.8%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 ↗ 		80.8 reasoning
lmarena text 1409.9 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		74.1 preference
math level 5 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 math
otis mock aime 2024 2025 83.9%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 ↗ 		83.9 math
otis mock aime 2024 2025 60%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] lowPublished Jul 15, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		60.0 math
otis mock aime 2024 2025 84.4%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 ↗ 		84.4 math
swe bench verified 62.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Feb 12, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		62.3 coding
swe bench verified 58.4%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 ↗ 		58.4 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)

  • Aider polyglot · arrived Oct 8, 2026
  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026
  • SWE-bench Verified · arrived Oct 8, 2026

pending Awaiting (4)

  • Humanity’s Last Exam · carries 11% of expected weight
  • Official model cards via models.dev · carries 4% of expected weight
  • LiveBench · carries 11% of expected weight
  • Terminal-Bench · carries 5% 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.