whatmodel.sh / GPT-5.1-Codex

GPT-5.1-Codex

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

GPT-5.1-Codex is a closed-weights language model from OpenAI, released November 2025.

Catalogue identity notes

Comparison-only. Arena entry 'gpt-5.1-codex' (webdev). Released 2025-11: OpenAI API changelog, Nov 13 (2025): 'Released gpt-5.1-codex and gpt-5.1-codex-mini to the Responses API'. OpenAI model page: 'the underlying model snapshot will be regularly updated'; no dated update was found. Shut down 2026-07-23.

66.3±2.2comparison only: no current run option verifiedfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of GPT-5.1-Codex, out of 1132 with a score, then more from OpenAI.

#modelscorewhereRAMreleased
166o4-mini OpenAI66±1api $1.93/M2025-04
167Nova 2 Omni (Preview) Amazon66±7api $0.93/M2025-11
168GPT-5.1-Codex OpenAI66±2comparison only2025-11
169Grok 3 Preview (02-24) SpaceXAI (xAI)66±3comparison only2025-02
170Llama-xLAM-2-70b-fc-r Salesforce66±4local~29GB2025-03
more from OpenAI
1GPT-6 Astra OpenAI87±1api $20.00/M2026-09
3GPT-6.1 Sol OpenAI85±1api $4.00/M2026-09
7GPT-6 Sol OpenAI83±1api $4.00/M2026-09

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▅▇█▇▅▄▂▁ #135 of 549 * · 98% of its score · 2 tests

Beats Qwen3.5 Plus, Gemini 2.5 Pro, Kimi K2 Thinking here, though they rank higher overall. Trails Llama 3.1 Nemotron Ultra 253B v1, Solar Pro 4, Nemotron 3 Super 120B-A12B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena WebDev (Code Arena)1337.1 ✎▁▂▄▃▅█▄▇▆▄▁▁ beats 24/119avg 981▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 78%sharp
WebApp1K-Duo-React pass@1 (onekq-ai)74.3% ✎▁··▁·▁▁▁▆█▇█ beats 35/45hard · avg 32%▇▇▇▇▇▇▇▇ 20%at its level

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 78%, WebApp1K models leaderboard (… 20%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 78%CC BY 4.0
WebApp1K models leaderboard (onekq-ai)1▇▇▇▇▇▇ 20%MIT
prior · pull toward the middle▇ 2%
weighted average= 66.3

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json