GPT-4.1
GPT-4.1 is an API-only (closed weights) language model from OpenAI, released April 14, 2025. The context window is 1M tokens. On the Epoch Capabilities Index it scores 136.2, rank 137 of 256 rated models. API price: $2 input / $8 output per million tokens.
Check it against your own PC →
Lab
OpenAI
Released
April 14, 2025
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$2 / $8 in / out
Epoch ECI
136.2 #137
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 8.0 | Chess Puzzles, SimpleBench, Humanity's Last Exam |
| Math | 21.3 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-Tier-4-2025-07-01-Private, FrontierMath-Tiers-1-3-v2-Private |
| Coding | 34.2 | Aider polyglot, SWE-bench Verified |
| Knowledge | 53.3 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 83.0% |
| GPQA Diamond | 58.2% |
| Aider Polyglot | 52.4% |
| SWE-bench Verified | 48.5% |
| OTIS Mock AIME | 38.3% |
| SimpleQA Verified | 31.1% |
| SimpleBench | 12.4% |
| Chess Puzzles | 6.4% |
| FrontierMath (Tiers 1–3) | 6.3% |
| Humanity's Last Exam | 5.4% |
| FrontierMath-Tier-4-2025-07-01-Private | 0.0% |
Links
Models with a similar score
Grok-3 mini · Qwen3.5-9B · GPT-5 nano · DeepSeek-R1 · Qwen3-235B-A22B · Qwen3-30B-A3B-Thinking (Jul 2025) · Qwen3-235B-A22B-Instruct (Jul 2025) · Grok 3
More from OpenAI
GPT-6.1 Terra · GPT-6.1 Sol · GPT-6 Sol · GPT-6 Luna · GPT-6 Astra · GPT-5.6 Cyber · Daybreak Red · Daybreak Blue