GPT-4.1
ModelActiveby OpenAI · family “gpt”
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and... (description from the OpenRouter listing)
in: imagein: textin: fileout: textTool useStructured output
Epoch Capabilities Index
136.8 #127 of 268
90% CI 133.4 – 138.5
Released
14 Apr 2025
Context window
1.05M tokens
Max output
33K tokens
Input $ / 1M tokens
$2.00
Output $ / 1M tokens
$8.00
Cached input $ / 1M
$0.50
Each benchmark shown separately with its own source
Benchmark results (20)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| LMCA | agents | 25.6% | 39% | — | — | External ↗ |
| DTBench | reasoning | 68.3% | 69% | — | — | External ↗ |
| FrontierMath-Tiers-1-3-v2-Private | math | 6.0% ±1.4 | 6% | — | 27 Aug 2026 | Eval log ↗ |
| Chess Puzzles | games | 6.0% ±2.4 | 8% | — | 7 Aug 2026 | Eval log ↗ |
| SimpleQA Verified | knowledge | 31.1% ±1.5 | 41% | — | 31 Aug 2026 | Eval log ↗ |
| FrontierMath-Tier-4-2025-07-01-Privatesuperseded | math | 0.0% | 0% | — | 1 Jul 2025 | Epoch ↗ |
| CadEval | coding | 42.0% | 57% | — | — | External ↗ |
| ARC-AGI-2 | reasoning | 0.4% | 0% | — | — | External ↗ |
| GeoBench | multimodal | 72.0% | 82% | — | — | External ↗ |
| FrontierMath-2025-02-28-Privatesuperseded | math | 5.5% ±1.3 | 11% | — | 14 Apr 2025 | Epoch ↗ |
| Fiction.LiveBench | long-context | 63.9% | 66% | — | — | External ↗ |
| HLE | knowledge | 5.4% | 10% | — | — | External ↗ |
| WeirdML | coding | 39.0% ±0.0 | 42% | — | — | External ↗ |
| Aider polyglot | coding | 52.4% | 60% | — | — | External ↗ |
| OTIS Mock AIME 2024-2025 | math | 38.3% ±6.3 | 38% | — | 14 Apr 2025 | Eval log ↗ |
| SimpleBench | reasoning | 27.0% | 33% | — | — | External ↗ |
| SWE-Bench verified | coding | 48.5% ±2.3 | 58% | — | 8 Feb 2026 | Eval log ↗ |
| GPQA diamond | science | 66.9% ±2.8 | 70% | — | 14 Apr 2025 | Eval log ↗ |
| MATH level 5 | math | 83.0% ±0.8 | 85% | — | 14 Apr 2025 | Epoch ↗ |
| ARC-AGI | reasoning | 5.5% | 6% | — | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
13 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.
Events
- Benchmark29d agoEpoch AI evaluates GPT-4.1Epoch AI Benchmarking Hub
- Benchmark33d agoEpoch AI evaluates GPT-4.1Epoch AI Benchmarking Hub