GPT-4.1
| Released | 2025-04-14 |
|---|---|
| Price per 1M | $2.00 in · $8.00 out |
| Overall score | 44.3 · rank 163 |
| Context window | 1,047,576 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 44.3 | 163 | 23 |
| Overall: Coding | 42.8 | 172 | 11 |
| Overall: Reasoning | 43.0 | 172 | 14 |
| Overall: Agentic work | 43.9 | 167 | 11 |
| Overall: Frontend | 43.9 | 150 | 6 |
| Coding | 42.0 | 171 | 3 |
| Agents | 45.1 | 136 | 1 |
| Reasoning | 42.3 | 171 | 7 |
| Math | 43.2 | 153 | 4 |
| Knowledge | 44.3 | 119 | 3 |
| General | 50.2 | 106 | 2 |
| Multimodal | 49.3 | 75 | 3 |
| Value vs price | −7.2 | 165 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 44.2 ±1.0 | 20 |
| High | 42.8 ±4.0 | 4 |
Evidence
Coding 42.0 ±2.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SWE-bench Verified (Epoch run) | 48.5% | Epoch AI | 2026-02-08 |
| Aider Polyglot | 52.4% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 54.7% | Vals AI | 2026-09-01 |
Agents 45.1 ±3.6
Reasoning 42.3 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 0.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 0.4% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 5.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 5.5% | Epoch AI | 2026-11-11 |
| EnigmaEval | 2.2% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 66.9% | Epoch AI | 2025-04-14 |
| GPQA Diamond (Vals run) | 65.4% | Vals AI | 2026-09-01 |
| Kagi Reasoning Benchmark | 52.3% | Kagi | 2026-11-11 |
| Chess Puzzles | 11.0% | Epoch AI | 2026-10-13 |
| SimpleBench | 27.0% | SimpleBench | 2026-11-11 |
| SimpleBench | 27.0% | Epoch AI | 2026-11-11 |
Math 43.2 ±1.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 83.0% | Epoch AI | 2025-04-14 |
| FrontierMath Tiers 1-3 | 6.0% | Epoch AI | 2026-08-27 |
| FrontierMath Tier 4 (2025 set) | 0.0% | Epoch AI | 2025-07-01 |
| OTIS Mock AIME 2024-2025 | 38.3% | Epoch AI | 2025-04-14 |
| FrontierMath Tiers 1-3 (2025 set) | 5.5% | Epoch AI | 2025-04-14 |
Knowledge 44.3 ±5.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 31.1% | Epoch AI | 2026-08-31 |
| Humanity's Last Exam | 5.4% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 80.5% | Vals AI | 2026-09-01 |
General 50.2 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 1,420 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,415 | LMArena | 2026-11-09 |
Multimodal 49.3 ±9.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,214 | LMArena | 2026-11-09 |
| MMMU-Pro (Vals run) | 72.4% | Vals AI | 2026-09-01 |
| GeoBench | 72.0% | Epoch AI | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| BFCL v4 | 39.4% | BFCL | A stronger configuration result was used |
Names matched to this model
gpt-4-1, gpt-4-1-2025-04-14