OpenAIGPT-5.5 Pro
Not yet ranked: too few independent results so far. Released 23 Apr 2026.
- Blended price
- $67.50/M
- $30.00 in · $180.00 out
- Output speed
- 4 tok/s
- First answer
- 3.49 s
- Context
- 1.1M
- Reasoning70
- Maths75
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 | – | – | 4 tok/s | 3.49 s | $0.066 | Reasoning 71 |
| xhighbest | – | – | 4 tok/s | 3.49 s | $0.066 | Maths 75 · Reasoning 70 |
| default | – | – | 4 tok/s | 3.49 s | $0.066 | Reasoning 72 |
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 | xhigh | default | Source |
|---|---|---|---|---|
| SimpleBench | 76.9%#4 | – | 76.9%#4 | SimpleBench |
| ARC-AGI-1 | 96.5%#13 | 95.0%#22 | – | ARC Prize |
| ARC-AGI-2 | 84.6%#19 | 84.2%#22 | – | ARC Prize |
Maths
| Benchmark | high | xhigh | default | Source |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | 87.7%#4 | – | Epoch AI Benchmarking Hub |
| FrontierMath Tier 4 | – | 78.0%#11 | – | Epoch AI Benchmarking Hub |
Composite
| Benchmark | high | xhigh | default | Source |
|---|---|---|---|---|
| Epoch Capabilities Indexnot in index | – | – | 162.3#5 | Epoch AI Benchmarking Hub |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| OpenAI | 4 tok/s | 3.49 s | $30.00 | $180.00 | 1.1M | – |
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 | $0.066 | – | 1.3 min |
| Summarise a 30-page report | 12,000 / 600 | $0.468 | – | 2.6 min |
| Code edit | 6,000 / 1,500 | $0.450 | – | 6.3 min |
| Agentic coding session | 60,000 / 4,000 | $2.52 | – | 16.7 min |
| Structured extraction | 2,000 / 200 | $0.096 | – | 53.5 s |
See also
Data as of 9 Sept 2026. Compare these configurations.