GPT-5 High
| Released | 2025-08-07 |
|---|---|
| Price per 1M | $1.25 in · $10.00 out |
| Overall score | 53.5 · rank 220 |
| Context window | 400,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | High |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 53.5 | 220 | 28 |
| Overall: Coding | 52.1 | 234 | 15 |
| Overall: Reasoning | 54.9 | 192 | 15 |
| Overall: Agentic work | 53.1 | 231 | 14 |
| Overall: Frontend | 48.6 | 235 | 9 |
| Coding | 53.3 | 211 | 5 |
| Agents | 52.6 | 178 | 2 |
| Reasoning | 54.5 | 209 | 7 |
| Math | 55.5 | 113 | 5 |
| Knowledge | 54.8 | 79 | 3 |
| Frontend | 45.5 | 147 | 1 |
| General | 55.2 | 114 | 2 |
| Multimodal | 53.2 | 93 | 3 |
| Value vs price | −0.2 | 250 |
Evidence
Coding 53.3 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 88.0% | Epoch AI | 2026-11-11 |
| MirrorCode | 4.4% | Epoch AI | 2026-10-21 |
| GSO | 6.9% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 85.9% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 73.6% | Epoch AI | 2026-02-06 |
| SWE-bench Verified (Vals run) | 69.0% | Vals AI | 2026-09-01 |
Agents 52.6 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| METR task suite | 69.4% | Epoch AI | 2026-11-11 |
| DeepResearch Bench | 48.1% | Epoch AI | 2026-11-11 |
Reasoning 54.5 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 9.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 9.9% | ARC Prize | 2026-11-11 |
| CritPt | 12.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 65.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 65.7% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 86.2% | Epoch AI | 2025-10-29 |
| GPQA Diamond (Vals run) | 85.6% | Vals AI | 2026-09-01 |
| Chess Puzzles | 36.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 56.7% | SimpleBench | 2026-11-11 |
| SimpleBench | 56.7% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 23.0% | Epoch AI | 2026-08-05 |
Math 55.5 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 55.4% | Epoch AI | 2026-06-10 |
| MATH Level 5 | 98.1% | Epoch AI | 2025-10-29 |
| FrontierMath Tier 4 | 22.0% | Epoch AI | 2026-06-11 |
| ProofBench | 18.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 91.4% | Epoch AI | 2025-10-29 |
| FrontierMath Tiers 1-3 (2025 set) | 32.4% | Epoch AI | 2025-11-13 |
| FrontierMath Tier 4 (2025 set) | 12.5% | Epoch AI | 2025-10-30 |
Knowledge 54.8 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 50.1% | Epoch AI | 2026-08-27 |
| Humanity's Last Exam | 25.3% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 86.5% | Vals AI | 2026-09-01 |
Frontend 45.5 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 20.1% | Vals AI | 2026-11-09 |
General 55.2 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,435 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 73.1% | EQ-Bench | 2026-11-11 |
Multimodal 53.2 ±3.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,211 | LMArena | 2026-11-09 |
| MMMU-Pro (Vals run) | 81.5% | Vals AI | 2026-09-01 |
| VPCT | 66.0% | Epoch AI | 2026-11-11 |
Names matched to this model
gpt-5-high