GPT-4.1 (batch)
OpenAI · released Apr 14, 2025
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...
Specification
- Context window
- 1.05M
- Max output
- 33K
- Knowledge cutoff
- Jun 30, 2024
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
19.6
59th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.15
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- MMLU-Pro80.6%
- GPQA Diamond66.6%
- AA-LCR (long context)64.3%
- τ²-bench (Telecom)47.1%
- LiveCodeBench45.7%
- IFBench43.0%
- SciCode38.1%
- AIME 202534.7%
- Terminal-Bench Hard13.6%
- Humanity's Last Exam4.2%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 80.6% |
| GPQA Diamond | 66.6% |
| AA-LCR (long context) | 64.3% |
| τ²-bench (Telecom) | 47.1% |
| LiveCodeBench | 45.7% |
| IFBench | 43.0% |
| SciCode | 38.1% |
| AIME 2025 | 34.7% |
| Terminal-Bench Hard | 13.6% |
| Humanity's Last Exam | 4.2% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- North Mini Code (free)Cohere20.2
- GPT-5 NanoOpenAI20.1
- GLM 4.5Z.ai19.7
- Kimi K2 0711Moonshot AI19.7
- GPT-4.1 (batch)OpenAI19.6
- GPT-4.1OpenAI19.6
- o3 MiniOpenAI19.2
- o1-proOpenAI19.1
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| North Mini Code (free) | 20.2 |
| GPT-5 Nano | 20.1 |
| GLM 4.5 | 19.7 |
| Kimi K2 0711 | 19.7 |
| GPT-4.1 (batch) | 19.6 |
| GPT-4.1 | 19.6 |
| o3 Mini | 19.2 |
| o1-pro | 19.1 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $1
- Output / 1M tokens
- $4
- Cached input / 1M
- $0.25
- Blended 3:1
- $1.75
One task, estimated
$0.15
- Input tokens
- 50,000
- Output tokens
- 25,000
- Profile
- Standard
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,131
- Win rate
- 59.5%
- Strongest at
- Data visualisation
- Tournaments
- 84
Elo by category
Dot position on a 900–1,150 scale · Elo has no meaningful zero
- 1,131
- 1,121
- 1,061
- 1,035
- 905
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Data visualisation | 1131 | 59.5% |
| Game development | 1121 | 59.1% |
| Websites | 1061 | 52.3% |
| UI components | 1035 | 49.7% |
| 3D scenes | 905 | 30.9% |