# GPT-5.1 CodexHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-1-codex-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-1-codex-high.

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-1-codex-high
Last updated: Thu, 22 Oct 2026 07:32:33 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Vibe Code Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Avibe-code%3Aoverall.md) | 13.12% | SE ±3.16 pp | 50 / 59 | $3.8 | 3,026.07source duration |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 13.115 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.797914 \| USD \| per_test \| Lower is better \| \| `latency` \| 3026.069 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.16 pp sourcePopulation 116 stderr 3.161 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) Source Vals AI Original model label openai/gpt-5.1-codex Source version 1.1 Observed 2026-10-22T02:10:23.531Z Evidence SHA-256 `0e8c23f521a0f751c5592952620e197b376cade41c78578461b7aa5740a173e7` Source locator `/tasks/overall/openai~1gpt-5.1-codex` |  |  |  |  |  |  |

---
Cite as: GPT-5.1 CodexHigh — Benchize, https://benchize.com/models/gpt-5-1-codex-high (retrieved 2026-10-22)