GPT-4.1 mini High
| Released | 2025-04-14 |
|---|---|
| Price per 1M | $0.40 in · $1.60 out |
| Overall score | 42.9 · rank 358 |
| Context window | 1,047,576 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | High |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 42.9 | 358 | 4 |
| Overall: Coding | 43.0 | 354 | 2 |
| Overall: Reasoning | 43.1 | 348 | 2 |
| Overall: Agentic work | 43.4 | 349 | 2 |
| Overall: Frontend | 43.2 | 317 | 2 |
| Coding | 42.7 | 318 | 1 |
| Reasoning | 44.6 | 328 | 1 |
| Knowledge | 39.7 | 186 | 1 |
| Multimodal | 44.8 | 142 | 1 |
| Value vs price | −6.2 | 324 |
Evidence
Coding 42.7 ±5.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveCodeBench (Vals run) | 58.2% | Vals AI | 2026-09-01 |
Reasoning 44.6 ±4.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond (Vals run) | 67.9% | Vals AI | 2026-09-01 |
Knowledge 39.7 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 77.2% | Vals AI | 2026-09-01 |
Multimodal 44.8 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 70.5% | Vals AI | 2026-09-01 |
Names matched to this model
gpt-4-1-mini-high