GPT-4.1 Mini (batch)
OpenAI · released Apr 14, 2025
GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...
Specification
- Context window
- 1.05M
- Max output
- 33K
- Knowledge cutoff
- Jun 30, 2024
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
14.8
49th percentile
Coding
20.2
Coding Index
Agentic
1.8
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.03
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-Pro78.1%
- GPQA Diamond66.4%
- τ²-bench (Telecom)52.9%
- LiveCodeBench48.3%
- AIME 202546.3%
- AA-LCR (long context)45.3%
- SciCode40.4%
- IFBench38.3%
- Terminal-Bench Hard7.6%
- Humanity's Last Exam5.0%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| MMLU-Pro | 78.1% |
| GPQA Diamond | 66.4% |
| τ²-bench (Telecom) | 52.9% |
| LiveCodeBench | 48.3% |
| AIME 2025 | 46.3% |
| AA-LCR (long context) | 45.3% |
| SciCode | 40.4% |
| IFBench | 38.3% |
| Terminal-Bench Hard | 7.6% |
| Humanity's Last Exam | 5.0% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- gpt-oss-20bOpenAI15.2
- gpt-oss-20b (free)OpenAI15.2
- 15.0
- GPT-4.1 Mini (batch)OpenAI14.8
- GPT-4.1 MiniOpenAI14.8
- Mistral Medium 3.1Mistral AI14.7
- Solar Pro 3Upstage14.5
- Llama 4 MaverickMeta14.5
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| gpt-oss-20b | 15.2 |
| gpt-oss-20b (free) | 15.2 |
| Nemotron 3 Nano Omni (free) | 15.0 |
| GPT-4.1 Mini (batch) | 14.8 |
| GPT-4.1 Mini | 14.8 |
| Mistral Medium 3.1 | 14.7 |
| Solar Pro 3 | 14.5 |
| Llama 4 Maverick | 14.5 |
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
- $0.2
- Output / 1M tokens
- $0.8
- Cached input / 1M
- $0.05
- Blended 3:1
- $0.35
One task, estimated
$0.03
- 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
- 1,112
- Win rate
- 58.5%
- Strongest at
- Game development
- Tournaments
- 224
Elo by category
Dot position on a 875–1,125 scale · Elo has no meaningful zero
- 1,112
- 1,060
- 1,020
- 996
- 892
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Game development | 1112 | 58.5% |
| Data visualisation | 1060 | 49.2% |
| Websites | 1020 | 47.8% |
| UI components | 996 | 45.4% |
| 3D scenes | 892 | 30.5% |