# GPT-5.2 Codex > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-2-codex. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-2-codex. OpenAI Canonical URL: https://benchize.com/models/gpt-5-2-codex Last updated: Thu, 22 Oct 2026 08:20:15 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 | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,329.34 | — | 86 / 97 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1329.3444189073916 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev ### Reported statistics lower 1318.7726514711678 rank 116 upper 1339.9161863436157 variance 29.09370422599189 votes 4355 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.2-Codex Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/622/row` | | | | | | | | | [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,348.39 | — | 89 / 106 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1348.3905375739141 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev ### Reported statistics lower 1333.2263317242803 rank 120 upper 1363.5547434235482 variance 59.86088873615002 votes 2359 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.2-Codex Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/479/row` | | | | | | | | | [LiveCodeBench / hard](https://benchize.com/benchmarks/vals-ai%3Alcb%3Ahard.md) | 74.57% | SE ±2.33 pp | 8 / 43 | $0.28 | 409.15source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.571 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.279114 \| USD \| per_test \| Lower is better \| \| `latency` \| 409.148 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.33 pp sourcePopulation 143 stderr 2.328 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5.2-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/hard/openai~1gpt-5.2-codex` | | | | | | | | | [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 993elo | SE ±8.4 | 30 / 31 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 993 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion gpt-5.2-codex variationName public ### Reported statistics Uncertainty Standard error: ±8.4 averageGenerationTimeMs Not reported battles 2158 losses 1355 standardError 8.3991 winRate 37.2 wins 803 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label GPT-5.2 Codex Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/47` | | | | | | | | | [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,051elo | SE ±6.63 | 37 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1051 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion gpt-5.2-codex variationName public ### Reported statistics Uncertainty Standard error: ±6.63 averageGenerationTimeMs Not reported battles 3426 losses 2068 standardError 6.6297 winRate 39.6 wins 1358 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label GPT-5.2 Codex Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/49` | | | | | | | | | [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,338.8 | — | 90 / 107 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1338.7964313466746 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev ### Reported statistics lower 1329.8646054033811 rank 121 upper 1347.728257289968 variance 20.76750484777439 votes 6718 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.2-Codex Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/120/row` | | | | | | | | | [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,338.8 | — | 90 / 107 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1338.7964313466746 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1329.8646054033811 rank 121 upper 1347.728257289968 variance 20.76750484777439 votes 6718 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.2-Codex Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/332/row` | | | | | | | | | [SWE-Bench Pro](https://benchize.com/benchmarks/scale%3Aswe_bench_pro.md) | 41.04source score | CI 37.47–44.61 | 2 / 7 | — | — | [scale](https://labs.scale.com/leaderboard/swe_bench_pro) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 41.04 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-5.2-codex sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 37.47–44.61 contaminationWarning Not reported rank 11 reportedConfidenceHalfWidth 3.57 ### Source [Original source](https://labs.scale.com/leaderboard/swe_bench_pro) Source scale Original model label gpt-5.2-codex Observed 2026-10-22T03:30:08.529Z Evidence SHA-256 `ccf74273c008225d50a7bed80dece7fdece51ccfc94cbeec19bb9f445376f7cc` Source locator `/rows/10` | | | | | | | | | [LiveCodeBench / overall](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aoverall.md) | 87.99% | SE ±0.94 pp | 8 / 43 | $0.12 | 168.27source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.993 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.11667 \| USD \| per_test \| Lower is better \| \| `latency` \| 168.271 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.94 pp sourcePopulation 143 stderr 0.942 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5.2-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/overall/openai~1gpt-5.2-codex` | | | | | | | | | [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 72.8% | — | 5 / 63 | — | — | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 72.8 \| percent \| verified \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-5-2-codex"] Reasoning effort Not reported sourceSubmission 20260219_mini-v2.0.0_gpt-5-2-codex subset Verified system ["System: Attempts - 1"] ### Reported statistics instanceCalls 28.072 instanceCost 0.4494238987 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 5.2 Codex Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/26` | | | | | | | | | [LiveCodeBench / medium](https://benchize.com/benchmarks/vals-ai%3Alcb%3Amedium.md) | 90.34% | SE ±1.51 pp | 9 / 43 | $0.06 | 85.05source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.339 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.063351 \| USD \| per_test \| Lower is better \| \| `latency` \| 85.052 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.51 pp sourcePopulation 143 stderr 1.51 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5.2-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/medium/openai~1gpt-5.2-codex` | | | | | | | | | [LiveCodeBench / easy](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aeasy.md) | 99.07% | SE ±0.54 pp | 1 / 43 | $0.00755 | 10.61source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 99.068 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007545 \| USD \| per_test \| Lower is better \| \| `latency` \| 10.612 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.54 pp sourcePopulation 143 stderr 0.535 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label openai/gpt-5.2-codex Source version 1 Observed 2026-10-22T02:10:28.824Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/easy/openai~1gpt-5.2-codex` | | | | | | | | | [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,089elo | SE ±9.15 | 31 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1089 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion gpt-5.2-codex variationName public ### Reported statistics Uncertainty Standard error: ±9.15 averageGenerationTimeMs Not reported battles 1767 losses 943 standardError 9.1477 winRate 46.6 wins 824 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label GPT-5.2 Codex Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/47` | | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,628 | — | 20 / 191 | — | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1628 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_2_codex ### Reported statistics coverageCount 27 draws 1 judged 87 losses 35 rank 28 ratingDeviation 28 wins 51 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.2-Codex Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/26` | | | | | | | | | [SWE-bench Multilingual](https://benchize.com/benchmarks/swe-bench%3Amultilingual.md) | 66.3% | — | 7 / 9 | — | — | [SWE-bench](https://www.swebench.com/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 66.3 \| percent \| multilingual \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-5-2-codex"] Reasoning effort Not reported sourceSubmission 20260220_mini-v2.0.0_gpt-5-2-codex subset Multilingual system ["System: Attempts - 1"] ### Reported statistics instanceCalls 38.17666666666667 instanceCost 0.6621715578333333 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 5.2 Codex Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/0/results/9` | | | | | | | | | [LiveBench](https://benchize.com/benchmarks/livebench%3Atasks.md) | 98% | — | 1 / 10 | — | — | [LiveBench](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 86.957 \| percent \| reported \| Higher is better \| \| `code_generation` \| 80.282 \| percent \| reported \| Higher is better \| \| `connections` \| 95 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 89.016 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 75 \| percent \| reported \| Higher is better \| \| `javascript` \| 68.182 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 68 \| percent \| reported \| Higher is better \| \| `math_comp` \| 95.098 \| percent \| reported \| Higher is better \| \| `olympiad` \| 86.997 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 67.05 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 56.035 \| percent \| reported \| Higher is better \| \| `python` \| 60 \| percent \| reported \| Higher is better \| \| `simplify` \| 60.567 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 74.783 \| percent \| reported \| Higher is better \| \| `summarize` \| 63.383 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 45.596 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 100 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 78.846 \| percent \| reported \| Higher is better \| \| `typescript` \| 20 \| percent \| reported \| Higher is better \| \| `typos` \| 70 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 70 \| percent \| reported \| Higher is better \| ### Configuration Model configuration gpt-5.2-codex sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label gpt-5.2-codex Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/13` | | | | | | | | --- Cite as: GPT-5.2 Codex — Benchize, https://benchize.com/models/gpt-5-2-codex (retrieved 2026-10-22)