# GPT-5 CodexHigh

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-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 |  |
| --- | --- | --- | --- | --- | --- | --- |
| [LiveCodeBench / overall](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aoverall.md) | 84.73% | SE ±1.03 pp | 22 / 43 | $0.1 | 134.96source duration |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.725 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.097451 \| USD \| per_test \| Lower is better \| \| `latency` \| 134.963 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.03 pp sourcePopulation 143 stderr 1.032 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/overall/openai~1gpt-5-codex` |  |  |  |  |  |  |
| [LiveCodeBench / hard](https://benchize.com/benchmarks/vals-ai%3Alcb%3Ahard.md) | 68.57% | SE ±2.48 pp | 21 / 43 | $0.23 | 323.06source duration |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.571 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.228984 \| USD \| per_test \| Lower is better \| \| `latency` \| 323.06 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.48 pp sourcePopulation 143 stderr 2.481 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/hard/openai~1gpt-5-codex` |  |  |  |  |  |  |
| [LiveCodeBench / medium](https://benchize.com/benchmarks/vals-ai%3Alcb%3Amedium.md) | 87.47% | SE ±1.69 pp | 24 / 43 | $0.06 | 73.01source duration |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.467 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.056783 \| USD \| per_test \| Lower is better \| \| `latency` \| 73.006 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.69 pp sourcePopulation 143 stderr 1.692 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/medium/openai~1gpt-5-codex` |  |  |  |  |  |  |
| [LiveCodeBench / easy](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aeasy.md) | 98.14% | SE ±0.75 pp | 30 / 43 | $0.00659 | 8.82source duration |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.137 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006587 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.824 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.75 pp sourcePopulation 143 stderr 0.754 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/easy/openai~1gpt-5-codex` |  |  |  |  |  |  |

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