OpenAI, released Apr 14, 2025

GPT-4.1price, context, benchmarks and release details

Provisional: not enough results to rank yet 100% confidence 100 percent, Full confidence, 6 of 9 expected sources in
41.5
SI Score
#124 of 142 ranked models
Input, per 1M tokens
$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/gpt-4.1 Retrieved Oct 9, 2026 · MIT
Open source ↗
Output, per 1M tokens
$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/gpt-4.1 Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
32.8Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Apr 14, 2025models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

How the score breaks down

Coding (weight 40 percent) 47.8
Math (weight 15 percent) 43.3
Preference (weight 15 percent) 71.4
Reasoning (weight 30 percent) 10.3

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

  1. 122 Gemma 3 27B IT 42.0
  2. 123 o3-mini 41.6
  3. 124 GPT-4.1 41.5
  4. 125 Claude Haiku 3.5 40.8
  5. 126 Claude Haiku 3 39.9

Full leaderboard

Benchmark results

12 benchmarks, 13 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

ARC-AGI-1 (public eval)reasoning 11.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] gpt-4-1-2025-04-14Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 11.8
ARC-AGI-1 (semi-private)reasoning 5.5%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-4-1-2025-04-14Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 5.5
ARC-AGI-2 (public eval)reasoning 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-4-1-2025-04-14Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 0.0
ARC-AGI-2 (semi-private)reasoning 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. [variant] gpt-4-1-2025-04-14Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 0.4
GPQA Diamondreasoning 66.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 66.9
Humanity's Last Exam (Scale AI)reasoning 5.4%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. [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 5.4
FrontierMath Tiers 1–3 (v2)math 6.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Aug 27, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 6.0
MATH Level 5math 83.0%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 83.0
OTIS Mock AIME 2024–2025math 38.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Apr 14, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 38.3
Aider Polyglotcoding 52.4%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Apr 14, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 52.4
SWE-bench Verifiedcoding 48.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 8, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 48.5 2 settings
  • Setting 1 48.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 8, 2026 Retrieved Oct 9, 2026 · CC-BY
    Open source ↗
  • Setting 2 39.6%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 ↗
About SWE-bench Verified
LMArena Textpreference 1382.9 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 71.4

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

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 ↗
First seen by SuperIndex
Oct 8, 2026
Coverage
80% of expected source weight

Reported (6)

  • Aider polyglotOct 8, 2026
  • ARC PrizeOct 8, 2026
  • Epoch AI BenchmarkingOct 8, 2026
  • Humanity’s Last ExamOct 8, 2026
  • LMArena / ArenaOct 8, 2026
  • SWE-bench VerifiedOct 8, 2026

Awaiting (3)

  • Official model cards via models.dev4% of weight
  • LiveBench11% of weight
  • Terminal-Bench5% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.

What changed

All releases · RSS feed

Alerts on this device

What to be alerted about
RSS feed