OpenAIReasoning modelo1
Best configuration ranks #230 of 610 on the BenchLeader Index at 53.2 ±4.3. Last measured 2 Sept 2026. Released 17 Dec 2024.
- Blended price
- $26.25/M
- $15.00 in · $60.00 out
- Output speed
- –
- First answer
- –
- Context
- 200k
- Overall index53
- Reasoning43
- Coding56
- Agents & tools42
- Maths50
- Knowledge59
- Instruction following69
- Human preference59
- Multimodal55
- Long context59
- Composite48
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | – | – | – | – | $0.024 | Maths 37 · Reasoning 55 |
| medium | 48.3 | #330 | – | – | $0.024 | Long context 48 · Maths 47 · Reasoning 48 |
| high | 44.3 | #417 | – | – | $0.024 | Agents & tools 24 · Coding 38 · Knowledge 55 · Maths 50 · Reasoning 49 |
| defaultbest | 53.2 | #230 | – | – | $0.024 | Agents & tools 42 · Coding 56 · Composite 48 · Human preference 59 · Instruction following 69 · Knowledge 59 · Long context 59 · Maths 50 · Multimodal 55 · Reasoning 43 |
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| GPQA Diamond | 74.2%#141 | 75.8%#131 | 76.8%#128 | 50.3%#200 | Epoch AI Benchmarking Hub |
| Humanity's Last Exam | – | – | – | 8.0%#32 | Scale AI / CAIS |
| SimpleBench | – | 36.7%#62 | 40.1%#60 | 41.7%#56 | SimpleBench |
| LMArena Hard Prompts | – | – | – | 1418#134 | LMArena |
| GPQA Diamond (AA)not in index | – | – | – | 76.5%#225 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | – | – | – | 7.0%#303 | Artificial Analysis |
| GPQA Diamond (Vals)not in index | – | – | 73.2%#83 | – | Vals AI |
Coding
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| WeirdML | – | – | 46.1%#78 | 47.6%#73 | WeirdML |
| LMArena Coding | – | – | – | 1433#147 | LMArena |
| LiveCodeBench | – | – | 50.3%#111 | – | Vals AI |
| Aider Polyglot | – | – | – | 61.7%#12 | Aider polyglot leaderboard |
| SWE-bench Verified (any scaffold)not in index | – | – | – | 64.6%#23 | SWE-bench |
Agents & tools
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| Cybench | – | – | – | 10.0%#15 | Cybench |
| APEX-Agents | – | – | 1.1%#62 | – | Mercor |
| Terminal-Bench Hard | – | – | – | 12.9%#199 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | – | – | – | 62.6%#171 | Artificial Analysis |
Maths
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 8.4%#92 | 10.2%#90 | 14.7%#87 | – | Epoch AI Benchmarking Hub |
| OTIS Mock AIME | 53.3%#161 | 73.3%#114 | 73.3%#114 | 31.1%#187 | Epoch AI Benchmarking Hub |
| MATH Level 5 | – | 94.4%#17 | 94.7%#16 | 81.7%#32 | Epoch AI Benchmarking Hub |
| AIME (Vals) | – | – | 71.5%#53 | – | Vals AI |
| MGSM | – | – | 89.3%#45 | – | Vals AI |
Knowledge
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| SimpleQA Verified | – | – | 41.1%#35 | – | Epoch AI Benchmarking Hub |
| AA-Omniscience | – | – | – | -11.1#150 | Artificial Analysis |
| MMLU-Pro | – | – | 83.5%#71 | – | Vals AI |
| LegalBench | – | – | 80.4%#79 | – | Vals AI |
| TaxEval | – | – | 74.3%#38 | – | Vals AI |
| MedQA | – | – | 96.5%#1 | – | Vals AI |
Instruction following
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| IFBench | – | – | – | 70.3%#68 | Artificial Analysis |
Human preference
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| LMArena Text | – | – | – | 1402#130 | LMArena |
Multimodal
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| LMArena Vision | – | – | – | 1168#90 | LMArena |
| VISTA | – | – | – | 45.3%#28 | Scale AI SEAL |
| MMMU (validation) | – | – | – | 78.2%#9 | MMMU |
Long context
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| Fiction.LiveBench 120k | – | 53.1%#20 | – | – | Fiction.live |
| AA-LCR | – | – | – | 65.0%#193 | Artificial Analysis |
Composite
| Benchmark | low | medium | high | default | Source |
|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | – | – | 141.9#89 | Epoch AI Benchmarking Hub |
| AA Intelligence Index | – | – | – | 15.2#220 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $7.50 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.024 | $0.022 | – |
| Summarise a 30-page report | 12,000 / 600 | $0.216 | $0.148 | – |
| Code edit | 6,000 / 1,500 | $0.180 | $0.146 | – |
| Agentic coding session | 60,000 / 4,000 | $1.14 | $0.802 | – |
| Structured extraction | 2,000 / 200 | $0.042 | $0.031 | – |
See also
Data as of 9 Sept 2026. Compare these configurations.