OpenAIReasoning modelGPT-5 Pro
Best configuration ranks #80 of 610 on the BenchLeader Index at 60.7 ±5.9. Last measured 13 Nov 2025stale: no new result in six months. Released 7 Aug 2025.
- Blended price
- $41.25/M
- $15.00 in · $120.00 out
- Output speed
- –
- First answer
- –
- Context
- 400k
- Overall index61
- Reasoning58
- Knowledge68
- Multimodal67
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 |
|---|---|---|---|---|---|---|
| high | – | – | – | – | $0.042 | Coding 57 · Maths 53 · Reasoning 60 |
| defaultbest | 60.7 | #80 | – | – | $0.042 | Knowledge 68 · Multimodal 67 · Reasoning 58 |
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 | high | default | Source |
|---|---|---|---|
| Humanity's Last Exam | – | 31.6%#9 | Scale AI / CAIS |
| SimpleBench | 61.6%#24 | 61.6%#24 | SimpleBench |
| Kagi LLM Benchmark | – | 76.8%#11 | Kagi LLM Benchmark |
| ARC-AGI-1 | – | 70.2%#97 | ARC Prize |
| ARC-AGI-2 | – | 18.3%#96 | ARC Prize |
Maths
| Benchmark | high | default | Source |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 55.8%#33 | – | Epoch AI Benchmarking Hub |
| FrontierMath Tier 4 | 19.5%#41 | – | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | high | default | Source |
|---|---|---|---|
| PRBench Finance | – | 51.1%#6 | Scale AI SEAL |
| PRBench Legal | – | 49.9%#7 | Scale AI SEAL |
| MultiNRC | – | 65.2%#2 | Scale AI SEAL |
Multimodal
| Benchmark | high | default | Source |
|---|---|---|---|
| VISTA | – | 52.4%#3 | Scale AI SEAL |
Composite
| Benchmark | high | default | Source |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | 150.3#41 | Epoch AI Benchmarking Hub |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.042 | – | – |
| Summarise a 30-page report | 12,000 / 600 | $0.252 | – | – |
| Code edit | 6,000 / 1,500 | $0.270 | – | – |
| Agentic coding session | 60,000 / 4,000 | $1.38 | – | – |
| Structured extraction | 2,000 / 200 | $0.054 | – | – |
See also
Data as of 9 Sept 2026. Compare these configurations.