SI Index Data as of Oct 9, 2026

GPT-5: Price, Context, Benchmarks, and Release Details

OpenAI · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:50 UTC
55.7
SI Score (method si-v3-retained-evidence-2)
#83 of 140 ranked
100% confidence 100 percent, Full confidence — 8 of 10 expected sources in
Coverage 86% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 66.7
Math (weight 15 percent) 55.6
Preference (weight 15 percent) 73.7
Reasoning (weight 30 percent) 35.2

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
$1.25models.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-5 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-5 Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
400Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Aug 7, 2025OpenAI 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, imagemodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

35 results
Benchmark Raw result Normalized (0–100) Pillar
aider polyglot 81.3%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Aug 25, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 		81.3 coding
arc agi v1 public eval 65.9%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		65.9 reasoning
arc agi v1 public eval 48.4%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		48.4 reasoning
arc agi v1 public eval 63.4%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-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		63.4 reasoning
arc agi v1 semi private 65.7%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		65.7 reasoning
arc agi v1 semi private 44%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		44.0 reasoning
arc agi v1 semi private 56.2%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-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		56.2 reasoning
arc agi v2 public eval 9.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		9.6 reasoning
arc agi v2 public eval 2.5%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.5 reasoning
arc agi v2 public eval 7.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		7.6 reasoning
arc agi v2 semi private 9.9%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-5-2025-08-07-highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		9.9 reasoning
arc agi v2 semi private 1.9%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-5-2025-08-07-lowPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1.9 reasoning
arc agi v2 semi private 7.5%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-5-2025-08-07-mediumPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		7.5 reasoning
frontiermath tier 4 v2 22.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 11, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		22.0 math
frontiermath tiers 1 3 v2 55.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jun 10, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		55.4 math
frontiermath tiers 1 3 v2 37.2%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 ↗ 		37.2 math
frontiermath tiers 1 3 v2 18.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		18.2 math
gpqa diamond 86.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		86.2 reasoning
gpqa diamond 85.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		85.4 reasoning
gpqa diamond 71.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.7 reasoning
hle scale 25.3%Humanity’s Last ExamPotential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. Sampled at reasoning_effort: 'high'. [variant] Published Aug 7, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		25.3 reasoning
lmarena text 1406.1 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		73.7 preference
math level 5 98.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		98.1 math
math level 5 97.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 20, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		97.9 math
otis mock aime 2024 2025 91.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Oct 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		91.4 math
otis mock aime 2024 2025 87.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Aug 7, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		87.2 math
otis mock aime 2024 2025 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] minimalPublished Jul 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 math
swe bench pro public 41.8%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] public Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		41.8 coding
swe bench pro public 41.8%SWE-bench Pro (public)Published steward score [variant] Published Nov 26, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		41.8 coding
swe bench verified 73.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Feb 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		73.6 coding
swe bench verified 71.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Feb 5, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.5 coding
swe bench verified 65%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; medium; 1.7.0Published Aug 7, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		65.0 coding
swe bench verified 71.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] OpenHandsPublished Aug 7, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		71.8 coding
swe bench verified 71.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Prometheus-v1.2Published Sep 29, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		71.2 coding
swe bench verified 74.4%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Prometheus-v1.2.1Published Oct 15, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		74.4 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 (8)

  • Aider polyglot · arrived Oct 8, 2026
  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Humanity’s Last Exam · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026
  • SWE-bench Verified · arrived Oct 8, 2026
  • SWE-bench Pro (public) · arrived Oct 8, 2026

pending Awaiting (2)

  • LiveBench · carries 10% 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.