GPT-5 Minimal
| Released | 2025-08-07 |
|---|---|
| Price per 1M | $1.25 in · $10.00 out |
| Overall score | 47.3 (early, few results) |
| Context window | 400,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Minimal |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 47.3 | 10 | |
| Overall: Coding | 47.8 | 8 | |
| Overall: Reasoning | 45.2 | 8 | |
| Overall: Agentic work | 48.8 | 8 | |
| Agents | 50.3 | 2 | |
| Reasoning | 42.8 | 6 | |
| Math | 48.4 | 2 | |
| Value vs price | −6.4 |
Evidence
Agents 50.3 ±4.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepResearch Bench | 48.9% | Epoch AI | 2026-11-11 |
| BALROG | 32.8% | Epoch AI | 2026-11-11 |
Reasoning 42.8 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 0.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 71.7% | Epoch AI | 2026-07-20 |
| ARC-AGI-2 (ARC Prize verified) | 0.0% | ARC Prize | 2026-11-11 |
| CritPt | 0.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 6.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 6.0% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 11.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 14.0% | Epoch AI | 2026-08-27 |
Math 48.4 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 18.3% | Epoch AI | 2026-08-27 |
| OTIS Mock AIME 2024-2025 | 46.7% | Epoch AI | 2026-07-20 |
Names matched to this model
gpt-5-minimal