GPT-4.1
by OpenAI · United StatesA million-token non-reasoning model built for long-context retrieval and instruction following.
Specification
The numbers
- Maker
- OpenAI
- Released
- 2025-04
- Parameters
- Not reported
- Architecture
- Not reported
- Context window
- 1,047,576 tokens
- Max output
- 32,768 tokens
- Input
- Text, Image
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Knowledge cutoff
- 2024-06
- Licence
- Proprietary
- Availability
- Not reported
- Weights
- Not released
Cost
Price per million tokens
- Input
- $2.00 / M tokens
- Output
- $8.00 / M tokens
- Cached input
- $0.50
- Blended 3:1
- $3.50
Standard first-party API rate, excluding batch discounts. Reasoning models bill thinking tokens as output, so cost per answer can far exceed the cost per token suggests.
Published scores
Benchmarks
Figures published by OpenAI or taken from a public leaderboard. Row last checked 2026-08.
| Category | Score | Rank |
|---|---|---|
| ReasoningGPQA Diamond | 66.3% | 44 of 83 reporting the same tests |
| MathsCompetition mathematics, graded on the final answer | Not reported | — |
| CodingSWE-bench Verified | 54.6% | 27 of 33 reporting the same tests |
| KnowledgeMMLU-Pro | 80.5% | 6 of 77 reporting the same tests |
| MultimodalMMMU | 74.8% | 10 of 39 reporting the same tests |
| Instruction followingIFEval | 87.4% | 9 of 15 reporting the same tests |
| Human preferenceWhich answer people pick, blind | Not reported | — |
A category averages every benchmark in it that GPT-4.1 reports. The rank counts only models that report the same tests, so it never compares an average over three benchmarks against an average over one.
Every reported test
| MMLU-ProKnowledge | Rank 6 of 77 models reporting | |
|---|---|---|
| GPQA DiamondReasoning | Rank 44 of 83 models reporting | |
| AIME 2025Maths | Not reported | No figure published |
| MATH-500Maths | Not reported | No figure published |
| SWE-bench VerifiedCoding | Rank 27 of 33 models reporting | |
| SWE-bench ProCoding | Not reported | No figure published |
| Terminal-Bench 2.1Coding | Not reported | No figure published |
| Frontier-Bench v0.1Reasoning | Not reported | No figure published |
| Terminal-Bench 4.0Coding | Not reported | No figure published |
| LiveCodeBenchCoding | Not reported | No figure published |
| HumanEvalCoding | Not reported | No figure published |
| MMMUMultimodal | Rank 10 of 39 models reporting | |
| IFEvalInstruction following | Rank 9 of 15 models reporting | |
| LMArena EloHuman preference | Not reported | No figure published |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
Head to head
GPT-4.1 compared
Same maker
Other models from OpenAI
| GPT-5OpenAI | OpenAI | 400K | $1.25 | $10.00 | — | 85.7% | 94.6% | 74.9% | Proprietary |
| GPT-5 miniOpenAI | OpenAI | 400K | $0.25 | $2.00 | — | 82.3% | 91.1% | 71% | Proprietary |
| GPT-5 nanoOpenAI | OpenAI | 400K | $0.05 | $0.40 | — | 71.2% | 85.2% | — | Proprietary |
| gpt-oss-120bOpenAI | OpenAI | 131K | $0.10 | $0.50 | 80.9% | 80.1% | 92.5% | — | Apache 2.0 |
| gpt-oss-20bOpenAI | OpenAI | 131K | $0.05 | $0.20 | 73.2% | 71.5% | 90% | — | Apache 2.0 |
| o3OpenAI | OpenAI | 200K | $2.00 | $8.00 | — | 83.3% | 88.9% | 69.1% | Proprietary |
| o4-miniOpenAI | OpenAI | 200K | $1.10 | $4.40 | — | 81.4% | 92.7% | 68.1% | Proprietary |
| GPT-4.1 miniOpenAI | OpenAI | 1M | $0.40 | $1.60 | — | 65% | — | 23.6% | Proprietary |
| GPT-4.1 nanoOpenAI | OpenAI | 1M | $0.10 | $0.40 | — | 50.3% | — | — | Proprietary |
| o3-miniOpenAI | OpenAI | 200K | $1.10 | $4.40 | — | 79.7% | 87.3% | 49.3% | Proprietary |
| o1OpenAI | OpenAI | 200K | $15.00 | $60.00 | — | 78% | 79.2% | 48.9% | Proprietary |
| o1-miniOpenAI | OpenAI | 128K | $1.10 | $4.40 | — | 60% | 63.6% | — | Proprietary |
| GPT-4o miniOpenAI | OpenAI | 128K | $0.15 | $0.60 | 63.1% | 40.2% | — | — | Proprietary |
| GPT-4oOpenAI | OpenAI | 128K | $2.50 | $10.00 | 74.7% | 53.6% | — | — | Proprietary |
| GPT-4 TurboOpenAI | OpenAI | 128K | $10.00 | $30.00 | 63.7% | 48% | — | — | Proprietary |
| GPT-3.5 TurboOpenAI | OpenAI | 16K | $0.50 | $1.50 | 38% | — | — | — | Proprietary |