GPT-4o mini High
| Released | 2024-07-18 |
|---|---|
| Price per 1M | $0.15 in · $0.60 out |
| Overall score | 30.6 · rank 426 |
| Context window | 128,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | High |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 30.6 | 426 | 4 |
| Overall: Coding | 30.4 | 421 | 2 |
| Overall: Reasoning | 31.7 | 419 | 2 |
| Overall: Agentic work | 31.6 | 420 | 2 |
| Overall: Frontend | 31.1 | 388 | 2 |
| Coding | 29.5 | 362 | 1 |
| Reasoning | 34.9 | 408 | 1 |
| Knowledge | 24.3 | 217 | 1 |
| Multimodal | 35.9 | 171 | 1 |
| Value vs price | −15.9 | 370 |
Evidence
Coding 29.5 ±5.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveCodeBench (Vals run) | 26.4% | Vals AI | 2026-09-01 |
Reasoning 34.9 ±4.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond (Vals run) | 44.2% | Vals AI | 2026-09-01 |
Knowledge 24.3 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMLU-Pro (Vals run) | 62.7% | Vals AI | 2026-09-01 |
Multimodal 35.9 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 56.6% | Vals AI | 2026-09-01 |
Names matched to this model
gpt-4o-mini-high