whatmodel.sh / GPT-4o Search Preview (2025-03-11)
GPT-4o Search Preview (2025-03-11)
↗ share
+ contribute
GPT-4o Search Preview (2025-03-11) is a closed-weights language model from OpenAI, released March 2025. Licence: proprietary.
Catalogue identity notes
OpenAI API model gpt-4o-search-preview, the GPT-4o model trained to run web searches in Chat Completions. It has one snapshot, gpt-4o-search-preview-2025-03-11, which is the default the alias points to. Arena search entry 'api-gpt-4o-search' (organization openai, first published 2025-08-07). LMArena's open Search Arena battle dataset names this OpenAI system 'gpt-4o-search-preview', with '-high' and '-high-loc' variants that differ only in search_context_size or location. The Search Arena paper (arXiv 2506.05334v1, Table A1) lists 'api-gpt-4o-search-preview' as base model gpt-4o with the default config. OpenAI has no other GPT-4o search model on the API. The search_context_size behind the current leaderboard entry is not stated. Not the plain gpt-4o snapshots (gpt-4o-2024-08-06 / -11-20) and not gpt-4o-mini-search-preview.
Model information sources
$ how it compares
The LLMs ranked either side of GPT-4o Search Preview (2025-03-11), out of 1132 with a score, then more from OpenAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 458 | GPT-4 Turbo Preview (1106) | 54±1 | comparison only | ||
| 459 |  Olmo 3 7B Think DPO | 54±3 | local | ||
| 460 | GPT-4o Search Preview (2025-03-11) | 54±5 | api $4.38/M | ||
| 461 |  Llama3-OpenBioLLM-70B | 54±3 | local | ||
| 462 | GPT-4 Turbo Preview (0125) | 54±1 | comparison only | ||
| more from OpenAI | |||||
| 1 | GPT-6 Astra | 87±1 | api $20.00/M | ||
| 3 | GPT-6.1 Sol | 85±1 | api $4.00/M | ||
| 7 | GPT-6 Sol | 83±1 | api $4.00/M | ||
$ what it's good at
web search▂▃▂▆▄█▃▃▁▁·▁ #77 of 81 * · 89% of its score · 1 test
Beats GLM-4.5, Claude Haiku 4.5, Gemma 4 26B-A4B here, though they rank higher overall. Trails GPT-4.1 nano, GPT-4o mini (2024-07-18) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena search systems (style controlled) | 1081.0 ✎ | ▃·▁▁▂▂▂█▅▂▁▁ beats 0/30 | 89% |
$ where to run it
Through an API
api · $4.38/M · $2.5 in / $10 out per 1M tokens · 128k context · developers.openai.com ↗ · price sourceObserved 2026-10-10 on OpenAI's own GPT-4o Search Preview model page (Text tokens): input $2.5, output $10 per 1M tokens. Web search calls carry an extra per-call fee, which is not included (the page refers to the pricing page). Chat Completions only.
$ how the score was worked out · LMArena leaderboard dataset 89%
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
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 89% |
| prior · pull toward the middle | 11% | |
| weighted average | = 53.8 |
$ improve this page
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