Rankings / OpenAI
GPT 5.1 (2025-11-13)
proprietaryreleased 2025-11-13
BenchAtlas Index
as of 2026-07-14
high effort
rank #186
12 families · 5 categories · high
high effort
rank #195
10 families · 4 categories · medium
thinking
rank #212
6 families · 5 categories · medium
Benchmark evidence
143 results
agentic coding
| τ²-Bench | high effort | 81.9 % | independent | Artificial Analysis |
| τ²-Bench | no reasoning | 46.5 % | independent | Artificial Analysis |
| τ²-Bench subset=banking | high effort | 14.0 % | independent | Artificial Analysis |
coding
| LiveCodeBench v6 implementation=artificial-analysis | high effort | 86.8 % | independent | Artificial Analysis |
| LiveCodeBench v6 implementation=artificial-analysis | no reasoning | 49.4 % | independent | Artificial Analysis |
| SciCode | high effort | 43.3 % | independent | Artificial Analysis |
| SciCode | no reasoning | 36.5 % | independent | Artificial Analysis |
external indices
| AA Coding Index | high effort | 49.4 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | high effort | 36.9 points | independent | Artificial Analysis |
| Intelligence Index v4.1 | no reasoning | 20.4 points | independent | Artificial Analysis |
| AA Math Index | high effort | 94.0 points | independent | Artificial Analysis |
| AA Math Index | no reasoning | 38.0 points | independent | Artificial Analysis |
| ECI | 149.7 points | independent | Epoch AI Benchmarking Hub | |
| ECI | low effort | 149.7 points | independent | Epoch AI Benchmarking Hub |
| ECI | no reasoning | 149.7 points | independent | Epoch AI Benchmarking Hub |
| ECI | high effort | 149.7 points | independent | Epoch AI Benchmarking Hub |
| ECI | medium effort | 149.7 points | independent | Epoch AI Benchmarking Hub |
factuality
| MASK contamination=Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. | thinking | 86.3 % 85.6–87.1 | independent | Scale Labs |
| SimpleQA Verified | high effort | 48.9 % | independent | Epoch AI Benchmarking Hub 2025-12-09 |
human preference
| Chinese (style control)older version arena=text · category=chinese · style_control=true | high effort | 1495.7 1481.9–1509.4 | community | LMArena Leaderboard Dataset |
| Coding (style control)older version arena=text · category=coding · style_control=true | high effort | 1490.3 1483.2–1497.4 | community | LMArena Leaderboard Dataset |
| Expert (style control)older version arena=text · category=expert · style_control=true | high effort | 1481.1 1468.4–1493.8 | community | LMArena Leaderboard Dataset |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | high effort | 1480.5 1474.7–1486.3 | community | LMArena Leaderboard Dataset |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | high effort | 1478.9 1472.4–1485.5 | community | LMArena Leaderboard Dataset |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1477.4 1463.8–1491.1 | community | LMArena Leaderboard Dataset | |
| Coding (style control)older version arena=text · category=coding · style_control=true | 1473.9 1467.1–1480.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | high effort | 1473.8 1468.9–1478.8 | community | LMArena Leaderboard Dataset |
| French (style control)older version arena=text · category=french · style_control=true | high effort | 1470.0 1448.5–1491.5 | community | LMArena Leaderboard Dataset |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | high effort | 1469.0 1456.6–1481.5 | community | LMArena Leaderboard Dataset |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | high effort | 1466.7 1458.8–1474.6 | community | LMArena Leaderboard Dataset |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1465.6 1460.0–1471.2 | community | LMArena Leaderboard Dataset | |
| Polish (style control)older version arena=text · category=polish · style_control=true | 1464.6 1447.9–1481.3 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | high effort | 1463.3 1458.0–1468.5 | community | LMArena Leaderboard Dataset |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | high effort | 1462.7 1455.1–1470.4 | community | LMArena Leaderboard Dataset |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1462.3 1450.3–1474.2 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | high effort | 1460.4 1446.3–1474.5 | community | LMArena Leaderboard Dataset |
| Polish (style control)older version arena=text · category=polish · style_control=true | high effort | 1460.3 1442.5–1478.0 | community | LMArena Leaderboard Dataset |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | high effort | 1459.0 1452.4–1465.5 | community | LMArena Leaderboard Dataset |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | high effort | 1458.9 1447.6–1470.2 | community | LMArena Leaderboard Dataset |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | high effort | 1457.9 1452.6–1463.2 | community | LMArena Leaderboard Dataset |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1457.5 1451.2–1463.7 | community | LMArena Leaderboard Dataset | |
| French (style control)older version arena=text · category=french · style_control=true | 1457.4 1435.4–1479.4 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1456.4 1444.9–1468.0 | community | LMArena Leaderboard Dataset | |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1455.8 1448.1–1463.4 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1455.0 1450.3–1459.7 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | high effort | 1454.8 1445.5–1464.2 | community | LMArena Leaderboard Dataset |
| Overall (style control) arena=text · category=overall · style_control=true | high effort | 1454.6 1450.8–1458.4 | community | LMArena Leaderboard Dataset |
| Math (style control)older version arena=text · category=math · style_control=true | high effort | 1454.5 1442.7–1466.4 | community | LMArena Leaderboard Dataset |
| German (style control)older version arena=text · category=german · style_control=true | high effort | 1453.0 1429.9–1476.1 | community | LMArena Leaderboard Dataset |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1449.9 1439.0–1460.8 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1448.3 1440.9–1455.6 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | high effort | 1448.1 1441.6–1454.5 | community | LMArena Leaderboard Dataset |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | high effort | 1447.8 1428.2–1467.4 | community | LMArena Leaderboard Dataset |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | high effort | 1445.2 1437.7–1452.7 | community | LMArena Leaderboard Dataset |
| German (style control)older version arena=text · category=german · style_control=true | 1445.0 1422.6–1467.5 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1445.0 1435.8–1454.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | high effort | 1443.7 1438.8–1448.6 | community | LMArena Leaderboard Dataset |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1443.5 1437.2–1449.8 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1442.1 1437.0–1447.1 | community | LMArena Leaderboard Dataset | |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | 1441.1 1433.9–1448.4 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1438.6 1435.0–1442.3 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1438.6 1419.6–1457.6 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1436.9 1423.8–1450.0 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | high effort | 1436.3 1429.4–1443.3 | community | LMArena Leaderboard Dataset |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1436.1 1431.0–1441.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1430.7 1425.9–1435.4 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | high effort | 1429.5 1421.2–1437.8 | community | LMArena Leaderboard Dataset |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1427.1 1421.0–1433.2 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1424.9 1418.2–1431.6 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1423.0 1411.9–1434.0 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | high effort | 1420.1 1412.5–1427.7 | community | LMArena Leaderboard Dataset |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1410.0 1401.9–1418.1 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1406.5 1399.3–1413.8 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1394.9 1371.5–1418.3 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | high effort | 1392.0 1367.2–1416.9 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | high effort | 87.6 % | independent | Epoch AI Benchmarking Hub 2025-11-13 |
| GPQA Diamond implementation=artificial-analysis | high effort | 87.3 % | independent | Artificial Analysis |
| GPQA Diamond implementation=vals-ai | high effort | 86.6 % | independent | Vals AI |
| GPQA Diamond | medium effort | 85.0 % | independent | Epoch AI Benchmarking Hub 2025-11-17 |
| GPQA Diamond implementation=artificial-analysis | no reasoning | 64.3 % | independent | Artificial Analysis |
| Humanity's Last Exam implementation=artificial-analysis | high effort | 26.5 % | independent | Artificial Analysis |
| Humanity's Last Exam contamination=Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. · implementation=scale | thinking | 23.7 % 22.0–25.4 | independent | Scale Labs |
| Humanity's Last Exam implementation=artificial-analysis | no reasoning | 5.2 % | independent | Artificial Analysis |
| MMLU-Pro implementation=artificial-analysis | high effort | 87.0 % | independent | Artificial Analysis |
| MMLU-Pro implementation=vals-ai | high effort | 86.4 % | independent | Vals AI |
| MMLU-Pro implementation=artificial-analysis | no reasoning | 80.1 % | independent | Artificial Analysis |
long context instruction
| AA-LCR | high effort | 75.0 % | independent | Artificial Analysis |
| AA-LCR | no reasoning | 44.0 % | independent | Artificial Analysis |
| IFBench | high effort | 72.9 % | independent | Artificial Analysis |
| IFBench | no reasoning | 43.2 % | independent | Artificial Analysis |
| MultiChallenge | thinking | 63.4 % 61.3–65.5 | independent | Scale Labs |
multimodal
| MMMU implementation=vals-ai | high effort | 83.2 % | independent | Vals AI |
| VISTA | thinking | 43.8 % 42.5–45.2 | independent | Scale Labs |
professional
| CaseLaw | high effort | 73.4 % | independent | Vals AI |
| CorpFin | high effort | 63.8 % | independent | Vals AI |
| LegalBench | high effort | 85.7 % | independent | Vals AI |
| MedQA | high effort | 96.4 % | independent | Vals AI |
| TaxEval | high effort | 74.9 % | independent | Vals AI |
reasoning math
| AIME year=2025 · implementation=artificial-analysis | high effort | 94.0 % | independent | Artificial Analysis |
| AIME implementation=vals-ai | high effort | 93.3 % | independent | Vals AI |
| AIME year=2025 · implementation=artificial-analysis | no reasoning | 38.0 % | independent | Artificial Analysis |
| ARC-AGI-1older version split=public_eval · model_type=CoT | high effort | 77.1 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | high effort | 72.8 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | medium effort | 68.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | medium effort | 57.7 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | low effort | 44.0 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | low effort | 33.2 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | high effort | 18.3 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | high effort | 17.6 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | no reasoning | 12.4 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | medium effort | 8.4 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | medium effort | 6.5 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | no reasoning | 5.8 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | low effort | 2.2 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | low effort | 1.9 % | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | high effort | 1.2 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | high effort | 1.2 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | high effort | 0.7 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | high effort | 0.5 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | medium effort | 0.5 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | medium effort | 0.4 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | no reasoning | 0.4 % | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | medium effort | 0.3 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | medium effort | 0.3 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | low effort | 0.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | low effort | 0.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | low effort | 0.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | low effort | 0.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | no reasoning | 0.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=semi_private · model_type=CoT | no reasoning | 0.1 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=semi_private · model_type=CoT | no reasoning | 0.0 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-1older version split=public_eval · model_type=CoT | no reasoning | 0.0 usd_per_task | independent | ARC Prize Leaderboard |
| ARC-AGI-2 split=public_eval · model_type=CoT | no reasoning | 0.0 % | independent | ARC Prize Leaderboard |
| EnigmaEval contamination=Potential contamination warning: This model was evaluated after the public release of EnigmaEval, allowing model builder access to the prompts and solutions. | thinking | 11.2 % 9.4–13.0 | independent | Scale Labs |
| FrontierMath | high effort | 31.0 % | independent | Epoch AI Benchmarking Hub 2025-11-13 |
| FrontierMath | medium effort | 26.9 % | independent | Epoch AI Benchmarking Hub 2025-11-17 |
| FrontierMath | low effort | 17.3 % | independent | Epoch AI Benchmarking Hub 2025-11-25 |
| FrontierMath Tier 4older version | high effort | 12.5 % | independent | Epoch AI Benchmarking Hub 2025-11-13 |
| FrontierMath Tier 4older version | medium effort | 4.2 % | independent | Epoch AI Benchmarking Hub 2025-11-17 |
| FrontierMath | no reasoning | 2.1 % | independent | Epoch AI Benchmarking Hub 2025-11-25 |
| OTIS Mock AIME 2024–2025 | high effort | 88.6 % | independent | Epoch AI Benchmarking Hub 2025-11-13 |
| OTIS Mock AIME 2024–2025 | medium effort | 85.6 % | independent | Epoch AI Benchmarking Hub 2025-11-17 |
| OTIS Mock AIME 2024–2025 | low effort | 63.9 % | independent | Epoch AI Benchmarking Hub 2025-11-25 |
Agent + model results
systems, not bare-model scores
| agent + model Epoch Inspect harness + GPT 5.1 (2025-11-13) | SWE-bench Verified | 68.0 % | independent | Epoch AI Benchmarking Hub |
| agent + model mini-SWE-agent + GPT 5.1 (2025-11-13) | SWE-bench Verified | 66.0 % | unverified | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GPT 5.1 (2025-11-13) | SWE-bench bash-only | 66.0 % | unverified | SWE-bench Leaderboard |
| agent + model Epoch Inspect harness + GPT 5.1 (2025-11-13) | SWE-bench Verified | 65.9 % | independent | Epoch AI Benchmarking Hub |
| agent + model mini-SWE-agent + GPT 5.1 (2025-11-13) | SWE-bench bash-only | 0.3 usd_per_task | unverified | SWE-bench Leaderboard |
| agent + model mini-SWE-agent + GPT 5.1 (2025-11-13) | SWE-bench Verified | 0.3 usd_per_task | unverified | SWE-bench Leaderboard |
| agent + model Artificial Analysis harness + GPT 5.1 (2025-11-13) | Terminal-Bench 2.1 | 52.4 % | independent | Artificial Analysis |
| agent + model terminus-2 + GPT 5.1 (2025-11-13) | Terminal-Bench 2.0 | 47.6 % | community | Terminal-Bench Leaderboard |
| agent + model Artificial Analysis harness + GPT 5.1 (2025-11-13) | Terminal-Bench Hard | 45.5 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + GPT 5.1 (2025-11-13) | Terminal-Bench Hard | 22.7 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.