SI Index Data as of Oct 9, 2026

GPT-4o: Price, Context, Benchmarks, and Release Details

OpenAI · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:50 UTC
31.2
SI Score (method si-v3-retained-evidence-2)
#138 of 140 ranked
59% confidence 59 percent, Medium confidence — 3 of 6 expected sources in
Coverage 47% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 16.7
Math (weight 15 percent) —
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 1.5

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
$2.50models.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/gpt-4o Retrieved Oct 9, 2026 · MIT
Open source ↗
Output price / 1M
$10.00models.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/gpt-4o Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
128Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
16.4Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
May 13, 2024OpenAI API changelogPublished source fact Retrieved Oct 9, 2026 · factual citation
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

11 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 semi private 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] gpt-4o-2024-11-20Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.5 reasoning
arc agi v2 public eval 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-4o-2024-11-20Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		0.0 reasoning
arc agi v2 semi private 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-4o-2024-11-20Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		0.0 reasoning
swe bench pro public 3.6%SWE-bench Pro (public)Published steward score [variant] Published Sep 19, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		3.6 coding
swe bench verified 38.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Agentless-1.5Published Oct 28, 2024 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		38.8 coding
swe bench verified 26.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] AppMap NaviePublished Jun 15, 2024 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		26.2 coding
swe bench verified 38.4%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] AutoCodeRoverPublished Jun 28, 2024 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		38.4 coding
swe bench verified 27%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] EPAM AI/Run Developer AgentPublished Oct 16, 2024 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		27.0 coding
swe bench verified 32.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] MASAIPublished Jun 12, 2024 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		32.6 coding
swe bench verified 21.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 0.0.0Published Jul 20, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		21.6 coding
swe bench verified 23.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] SWE-agentPublished Jul 28, 2024 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		23.2 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 (3)

  • ARC Prize · arrived Oct 8, 2026
  • SWE-bench Verified · arrived Oct 8, 2026
  • SWE-bench Pro (public) · arrived Oct 8, 2026

pending Awaiting (3)

  • Official model cards via models.dev · carries 6% of expected weight
  • LiveBench · carries 16% of expected weight
  • LMArena / Arena · carries 31% 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.