Models / GPT-5.4 Pro
GPT-5.4 Pro
Early evidence, 3 results from 2 sources, on 1 use case. GPT-5.4 Pro is strongest at sticking to the facts; there is too little evidence yet to recommend it either way.
Results 16 Nov 2026 · 3 results · 2 sources
Test GPT-5.4 Pro on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $30.00 in · $180.00 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices - Speed
- Not measured
- Intelligence Index
- Not measured
- Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- OpenAI, based in the US
Weights not published - Released
- 5 Mar 2026
1,050,000 tokens of context
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | – | – | $67.50 blended, 100th percentilecheapest: Mistral Nemo | – |
| Models from developers based in the US | – | – | $67.50 blended, 100th percentilecheapest: Gemma 3 4B | – |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced $10 or more per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
- tau2-bench: has not measured this model.
- Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
- OpenHands Index: has not measured this model.
- Microsoft STATE-Bench: has not measured this model.
- Artificial Analysis: has not measured this model.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
- Artificial Analysis: has not measured this model.
WritingWhat people prefer in blind comparisons, and judged writing quality
- Arena (formerly LMArena): has not measured this model.
- UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | GPT-5.4 Pro | Rank among available | Best available |
|---|---|---|---|
| Vectara Hallucination LeaderboardVectara: hallucination rate · reported | 8.3% | 29th of 71 | GPT-5.4 nano 3.1% |
| SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported | 46.3% | 32nd of 68 | GPT-6 Astra 75.6% |
- Arena (formerly LMArena): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- OpenAI's newer, at least as capable modelGPT-6 Astra$20.00 blended · Intelligence Index 52.7Compare with GPT-5.4 Pro →
- The most capable open-weights modelMiMo-V2.6-Pro$0.54 blended · Intelligence Index 46.3
Against GPT-5.4 Pro at $67.50 blended. "Similar intelligence" means within 4 points or better.
Where to run it
2 hosts on OpenRouter at the standard service tier, with a median of $67.50 blended per million tokens. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| Azure | not stated | $30.00 | $180.00 | $67.50 |
| OpenAI | not stated | $30.00 | $180.00 | $67.50 |
Other service tiers, not counted above: OpenAI flex $15.00 in, $90.00 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.
Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| GPT-5.4 Pro | Claude Fable 5.2 leads overall | GPT-6.1 Sol OpenAI's best other model | Claude Opus 5.5 near the top overall | GPT-6.1 Terra near the top overall | |
|---|---|---|---|---|---|
| Price per million tokens | $67.50 | $16.00 | $4.00 | $8.00 | $2.00 |
| Tokens a second | – | – | 53 | 96 | – |
| Intelligence Index | – | – | 51.8 | 57.6 | – |
| Spring Prompt overall | – | 90 | 80 | 82 | 80 |
| Rank among available models, by use case | |||||
| Product listings | – | 5th | 2nd | 13th | 4th |
| Decks from an analysis | – | 4th | 5th | 7th | 8th |
| User surveys | – | 1st | 3rd | 4th | 8th |
| Marketing planning | – | 1st | – | 9th | 2nd |
| Agents and tool use | pending | – | 6th | 3rd | 7th |
| Professional work | – | – | 9th | 3rd | – |
| Reasoning and knowledge | – | – | 6th | 1st | 22nd |
| Writing | – | – | 16th | 5th | – |
| Sticking to the facts | 59th of 139 | – | 18th | 3rd | – |
| Speed under pressure | – | 8th | 3rd | – | 17th |
Shaded figures are better than GPT-5.4 Pro's. A dash means no result.
Where it has been measured
Among models available today, mid-field on sticking to the facts, the one use case measured. Results for agents and tool use are pending: those sources last updated before this model was released.
Not timed: Artificial Analysis, our source for speed, has not tested it
- SimpleQA Verified (Epoch AI)1 result
- Vectara Hallucination Leaderboard2 results
- Berkeley Function Calling Leaderboard (BFCL) V4Pending: latest results 16 Dec 2025
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- Arena (formerly LMArena)Not measured
- Artificial AnalysisNot measured
- GDP.pdfNot measured
- Microsoft STATE-BenchNot measured
- OpenHands IndexNot measured
- Remote Labor IndexNot measured
- tau2-benchNot measured
- UGI LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
3 published results from 2 sources, each in the source's own units, with the configuration that produced it.
SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| SimpleQA Verified: correct answers% of questions, higher is better | 46.3% | 35 of 85 | GPT-5.4 Pro (xhigh reasoning) | 27 Aug 2026 |
Not shown: Not answers grounded in your documents; tests what the model remembers.
Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Vectara: answer rate% of documents, higher is better | 100.0% | 1 of 108 | GPT-5.4 Pro | 22 Sep 2026 |
| Vectara: hallucination rate% of summaries, lower is better | 8.3% | 42 of 108 | GPT-5.4 Pro | 22 Sep 2026 |
Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.
Will GPT-5.4 Pro work for your product?
Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.
New here? Your email starts a free trial. No credit card needed.