GPT-5.5
| Released | 2026-04-23 |
|---|---|
| Price per 1M | $5.00 in · $30.00 out |
| Overall score | 60.7 · rank 21 |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 60.7 | 21 | 46 |
| Overall: Coding | 59.5 | 34 | 30 |
| Overall: Reasoning | 62.8 | 17 | 18 |
| Overall: Agentic work | 60.3 | 29 | 28 |
| Overall: Frontend | 57.5 | 45 | 12 |
| Coding | 59.5 | 32 | 8 |
| Agents | 59.6 | 35 | 10 |
| Reasoning | 64.5 | 15 | 10 |
| Math | 62.7 | 18 | 5 |
| Knowledge | 59.2 | 33 | 3 |
| Frontend | 56.0 | 48 | 2 |
| General | 61.8 | 20 | 6 |
| Multimodal | 61.0 | 13 | 2 |
| Value vs price | +5.7 | 68 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 60.4 ±3.2 | 12 |
| High | 59.4 ±1.8 | 15 |
| Low | 54.4 ±2.7 | 10 |
| Medium | 57.8 ±3.3 | 7 |
| Non-reasoning | 50.1 ±4.1 | 7 |
| Extra High | 61.1 ±0.8 | 32 |
Evidence
Coding 59.5 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepSWE | 67.0% | Epoch AI | 2026-11-11 |
| FrontierCode | 43.0% | Epoch AI | 2026-11-11 |
| MirrorCode | 23.3% | Epoch AI | 2026-10-29 |
| GSO | 40.2% | Epoch AI | 2026-11-11 |
| SciCode | 56.1% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 85.3% | Vals AI | 2026-09-01 |
| SWE-bench Verified (Epoch run) | 80.6% | Epoch AI | 2026-04-24 |
| ProgramBench | 0.5% | Vals AI | 2026-11-09 |
| SWE-bench Verified (Vals run) | 82.6% | Vals AI | 2026-09-01 |
Agents 59.6 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OSWorld 2.0 | 13.0% | Epoch AI | 2026-11-11 |
| SRE Bench | 3.8% | Vals AI | 2026-11-05 |
| APEX-Agents | 55.1% | Epoch AI | 2026-11-11 |
| Remote Labor Index | 6.3% | Epoch AI | 2026-11-11 |
| tau2-bench Banking Knowledge | 44.6% | tau2-bench | 2026-07-22 |
| Terminal-Bench 2.0 | 84.7% | Epoch AI | 2026-04-23 |
| Tax Agent Bench | 21.8% | Vals AI | 2026-11-09 |
| Terminal-Bench 2.1 (Vals run) | 76.4% | Vals AI | 2026-10-01 |
| SkillsBench | 62.2% | Vals AI | 2026-10-29 |
| DeepResearch Bench | 54.0% | Epoch AI | 2026-11-11 |
| Vending-Bench 2 | $7,524 | Epoch AI | 2026-11-11 |
Reasoning 64.5 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 85.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 85.0% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 96.2% | Lech Mazur | 2026-11-10 |
| CritPt | 27.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 95.0% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 95.0% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 94.0% | Epoch AI | 2026-04-24 |
| GPQA Diamond (Vals run) | 93.2% | Vals AI | 2026-09-01 |
| ARC-AGI-3 | 0.4% | ARC Prize | 2026-11-11 |
| Kagi Reasoning Benchmark | 88.8% | Kagi | 2026-11-11 |
| Chess Puzzles | 63.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 69.0% | SimpleBench | 2026-04-24 |
| SimpleBench | 69.0% | Epoch AI | 2026-11-11 |
| Mystery Game Puzzles | 56.0% | Epoch AI | 2026-07-24 |
Math 62.7 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 85.3% | Epoch AI | 2026-06-11 |
| FrontierMath Tier 4 | 72.5% | Epoch AI | 2026-06-11 |
| ProofBench | 50.0% | Epoch AI | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 100.0% | Epoch AI | 2026-04-24 |
| MathArena Final-Answer Competitions | 94.3% | MathArena | 2026-11-11 |
| FrontierMath Tiers 1-3 (2025 set) | 51.7% | Epoch AI | 2026-04-23 |
| FrontierMath Tier 4 (2025 set) | 35.4% | Epoch AI | 2026-04-23 |
Knowledge 59.2 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 63.0% | Epoch AI | 2026-08-27 |
| MMLU-Pro (Vals run) | 88.1% | Vals AI | 2026-09-01 |
| Legal Research Bench | 40.4% | Vals AI | 2026-11-09 |
Frontend 56.0 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 69.8% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,512 | LMArena | 2026-11-09 |
General 61.8 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,520 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,295 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 1,845 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,481 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 82.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 78.2% | EQ-Bench | 2026-11-11 |
Multimodal 61.0 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 88.3% | Vals AI | 2026-09-01 |
| LMArena Vision | 1,285 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 76.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 94.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 92.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 76.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 94.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 92.2% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 33.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 83.3% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 70.4% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 33.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 83.3% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 70.4% | ARC Prize | A stronger configuration result was used |
| Chess Puzzles | 9.0% | Epoch AI | A stronger configuration result was used |
| Chess Puzzles | 30.0% | Epoch AI | A stronger configuration result was used |
| CritPt | 1.4% | Epoch AI | A stronger configuration result was used |
| CritPt | 8.0% | Epoch AI | A stronger configuration result was used |
| CritPt | 25.4% | Epoch AI | A stronger configuration result was used |
| CritPt | 18.6% | Epoch AI | A stronger configuration result was used |
| DeepResearch Bench | 48.7% | Epoch AI | A stronger configuration result was used |
| DeepResearch Bench | 49.6% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 27.0% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 64.4% | Epoch AI | A stronger configuration result was used |
| DeepSWE | 54.0% | Epoch AI | A stronger configuration result was used |
| Extended NYT Connections | 22.0% | Lech Mazur | A stronger configuration result was used |
| Extended NYT Connections | 95.2% | Lech Mazur | A stronger configuration result was used |
| Extended NYT Connections | 92.4% | Lech Mazur | A stronger configuration result was used |
| GPQA Diamond | 77.3% | Epoch AI | A stronger configuration result was used |
| GPQA Diamond | 90.7% | Epoch AI | A stronger configuration result was used |
| LMArena Text | 1,476 | LMArena | A stronger configuration result was used |
| LMArena Vision | 1,283 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,455 | LMArena | A stronger configuration result was used |
| LMArena WebDev | 1,487 | LMArena | A stronger configuration result was used |
| MirrorCode | 10.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 18.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 28.0% | Epoch AI | A stronger configuration result was used |
| Mystery Game Puzzles | 52.0% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 57.8% | Epoch AI | A stronger configuration result was used |
| OTIS Mock AIME 2024-2025 | 84.4% | Epoch AI | A stronger configuration result was used |
| SciCode | 47.3% | Epoch AI | A stronger configuration result was used |
| SciCode | 51.6% | Epoch AI | A stronger configuration result was used |
| SciCode | 55.8% | Epoch AI | A stronger configuration result was used |
| SciCode | 54.5% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 83.2% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 82.3% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 82.0% | Epoch AI | A stronger configuration result was used |
| Terminal-Bench 2.0 | 66.1% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gpt-5-5, gpt-5-5-pre-release