OpenAIReasoning modelGPT-5.1-Codex-Max
Not yet ranked: too few independent results so far. Released 13 Nov 2025.
- Blended price
- $3.44/M
- $1.25 in · $10.00 out
- Output speed
- 29 tok/s
- First answer
- 4.29 s
- Context
- 400k
- Coding57
- Agents & tools63
- Maths36
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.
Coding
| Benchmark | max | Source |
|---|---|---|
| LiveCodeBench | 83.6%#46 | Vals AI |
| IOI | 21.4%#22 | Vals AI |
Agents & tools
| Benchmark | max | Source |
|---|---|---|
| Terminal-Bench | 60.4%#14 | Terminal-Bench |
Maths
| Benchmark | max | Source |
|---|---|---|
| ProofBench | 9.0%#50 | Vals AI |
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 |
|---|---|---|---|---|---|---|
| Azure | 29 tok/s | 4.29 s | $1.25 | $10.00 | 400k | – |
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 $0.125 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0035 | $0.0032 | 14.8 s |
| Summarise a 30-page report | 12,000 / 600 | $0.021 | $0.011 | 25.3 s |
| Code edit | 6,000 / 1,500 | $0.022 | $0.017 | 56.9 s |
| Agentic coding session | 60,000 / 4,000 | $0.115 | $0.064 | 2.4 min |
| Structured extraction | 2,000 / 200 | $0.0045 | $0.0028 | 11.3 s |
See also
Data as of 9 Sept 2026. Compare with another model.