OpenAI
Multimodal flagship model with native vision and audio capabilities. Combines high intelligence with fast response times at competitive pricing.
Multimodal flagship model with native vision and audio capabilities.
OpenRouter
Price record: 2026-11-17. Source: openrouter.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
43.7
Quality Score
1280
Arena ELO
Undisclosed
Parameters
128K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
17 of 22 public signals
Sign in to join the discussion
0
Downloads
0
Likes
Nov 2024
Released
4/5 signals
4/4 signals
5/5 signals
1/4 signals
3/4 signals
Parameters
—
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: API access · Speculative confidence
Gaps we are still tracking
Launches
3
Benchmarks
9
Safety
1
Research
6
General
5
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
SWE-Bench Verified resolved rate 21.6
SWE-Bench Verified resolved rate 21.6
View sourceSWE-Bench Verified resolved rate 32.6
View sourceNow in beta: Businesses in ChatGPT. Claim your business, manage your information, and get insights on how people engage with you. Eligible businesses can also build a Business Agent to answer customers’ questions and help them explore what you offer. https://t.co/N2GEZX0mFT https://t.co/lYj2Z48fhQ
We built Control Room, a central system to track model workloads across our research infrastructure and stop them quickly when safety or security concerns arise. It connects every research inference workload, including agentic sampling for model training and evaluation, data
A live esports broadcast needs a director who chooses which camera goes on air and a caster who talks over that choice, every second and without knowing what comes next. Streaming video language models have learned to commentate, but only over a broadcast that a human director has already produced. We study live broadcast production, in which a model receives the raw camera of every player and must both direct and commentate from the past alone. We present DirCast, a single streaming video language model that does both. Every second it scans all cameras at low resolution, decides with a hold-or-switch director whether and where to cut, and reads the chosen camera at high resolution before it speaks. Its context keeps what went on air and what was said and lets the other views expire, which bounds the cost of a stream of any length. We build a dataset of 27 professional Dota 2 matches with a camera for every hero, the human director's choices and the casters' commentary. DirCast directs better than rule-based and zero-shot directors including GPT-5, and its commentary wins 29.2 percent of comparisons against GPT-4o under the Proact-VL protocol, against 19.4 percent for the strongest of eleven streaming commentators that watch the human broadcast.
Enterprises adopting retrieval-augmented generation (RAG) face a recurring operational decision: promote, revise, or block a system version. The evidence is incomplete and the metrics come from fallible LLM judges. We report on AGO AI Quality Gate (AGO), an evidence-first quality-gate framework deployed in industrial RAG assessment engagements. AGO integrates four key components: a four-state decision model that treats missing data and judge errors as explicit outcomes; layered scoring combining deterministic checks, local guardrails, and structured LLM evaluation; a stratified beta-binomial gate that quantifies regression risk probabilistically; and a mandatory meta-evaluation protocol to validate the LLM judge before it influences decisions. Since engagement data is proprietary, we evaluate the judge layer on RAGBench, a public benchmark of 100k annotated RAG traces across 12 datasets. On identical stratified test samples (N=1200 per judge), a low-cost judge (gpt-4.1-nano) detects non-adherent answers barely above chance (AUROC 0.603 [0.570, 0.634]), despite producing flawless protocol output, while gpt-4o reaches 0.783 [0.756, 0.807] -- yet its per-domain performance still ranges from 0.62 to 0.88. A fixed-seed gate study spanning regression, no change, and improvement quantifies unsafe promotion, false-alarm cost, and improvement throughput. Under regression, the decision-grade profile reduces unsafe promotion to 22.2%-35.1%, against 29.3%-41.8% for a naive gate. These results support the design choices that judge quality must be measured per engagement and that point estimates alone are not a release decision.
Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native speech generation through a shared causal timeline for user inputs, model outputs, and delegation events. A dual-loop runtime coordinates live interaction with background reasoning and tool execution. Foreground interaction continues while Realtime-Venus-Harness executes tasks asynchronously and returns results for integration into the ongoing dialogue. Both models follow a common post-training recipe combining offline understanding, proactive full-duplex trajectories, and delegation workflows. Among the evaluated online models, Realtime-Venus-Omni achieves the highest scores on six of eight video benchmarks, including StreamingBench (70.2%), OVO-Bench (64.7%), and Daily-Omni (81.3%). Across eight audio understanding and spoken question answering benchmarks, Realtime-Venus-Audio leads the compared models on MMAU (78.0%), MMAU-Pro (63.2%), Llama Questions (83.8%), and Speech CMMLU (67.8%), while matching the best VoiceBench AlpacaEval score of 4.81. On Full-Duplex-Bench v1.5, Realtime-Venus-Audio responds to 75% of user interruptions and achieves continuation rates of 97%, 88%, and 86% under backchannels, other-directed speech, and background speech, respectively, exceeding Gemini 3.1 Live and GPT-4o on all three continuation metrics.
Reasoning models are evaluated on single-turn benchmarks but deployed in multi-turn dialogue, where users push back on correct answers. Under sustained adversarial pressure we find a previously undocumented failure mode: the chain-of-thought stays factually correct from first turn to last while the emitted answer flips wrong. We call this unfaithful capitulation (UC) and isolate it with a 2times 2 latent-versus-behavioral framework that flip-rate metrics and single-turn faithfulness probes both miss. Across three datasets (MT-Consistency, MMLU-Pro, GSM8K), the latent-correct rate at the behavioral flip clusters near 50% in think mode and collapses to 11-15% under no_think -- paired, within-model causal evidence that reasoning creates the gap. Across models the effect tracks the reasoning channel (high in Qwen3-32B and GPT-OSS-20B, low in inline-CoT Gemma-4-31B-it). An independent GPT-4o judge corroborates 86% of UC labels; a token-level probe shows the answer-slot argmax is correct in 84% of UC cells; and a naive trace-anchored defense backfires. We release all trajectories, traces, and judge labels.
Large Vision-Language Models (LVLMs) have shown significant progress in video understanding, yet they face substantial challenges in tasks requiring precise spatiotemporal localization at the instance level. Existing methods primarily rely on text prompts for human-model interaction, but these prompts struggle to provide precise spatial and temporal references, resulting in poor user experience. Furthermore, current approaches typically decouple visual perception from language reasoning, centering reasoning around language rather than visual content, which limits the model's ability to proactively perceive fine-grained visual evidence. To address these challenges, we propose VideoSeeker, a novel paradigm for instance-level video understanding through visual prompts. VideoSeeker seamlessly integrates agentic reasoning with instance-level video understanding tasks, enabling the model to proactively perceive and retrieve relevant video segments on demand. We construct a four-stage fully automated data synthesis pipeline to efficiently generate large-scale, high-quality instance-level video data. We internalize tool-calling and proactive perception capabilities into the model via cold-start supervision and RL training, building a powerful video understanding model. Experiments demonstrate that our model achieves an average improvement of +13.7% over baselines on instance-level video understanding tasks, surpassing powerful closed-source models such as GPT-4o and Gemini-2.5-Pro, while also showing effective transferability on general video understanding benchmarks. The relevant datasets and code will be released publicly.
Understanding user instructions and object spatial relations in surrounding environments is crucial for intelligent robot systems to assist humans in various tasks. The natural language and spatial reasoning capabilities of Vision-Language Models (VLMs) have the potential to enhance the generalization of robot planners on new tasks, objects, and motion specifications. While foundation models have been applied to task planning, it is still unclear the degree to which they have the capability of spatial reasoning required to enforce user preferences or constraints on motion, such as desired distances from objects, topological properties, or motion style preferences. In this paper, we evaluate the capability of four state-of-the-art VLMs at spatial reasoning over robot motion, using four different querying methods. Our results show that, with the highest-performing querying method, Qwen2.5-VL achieves 71.4% accuracy zero-shot and 75% on a smaller model after fine-tuning, and GPT-4o leads to lower performance. We evaluate two types of motion preferences (object-proximity and path-style), and we also analyze the trade-off between accuracy and computation cost in number of tokens. This work shows some promise in the potential of VLM integration with robot motion planning pipelines.
SWE-Bench Verified resolved rate 32.6
SWE-Bench Verified resolved rate 38.8
LiveCodeBench pass@1 38.3 across 1055 tasks
Introducing GPT-5 for developers | OpenAI Skip to main content Research Products Business Developers Company Foundation (opens in a new window) Log in Try ChatGPT (opens in a new window) Research Products Business Developers Company Foundation (opens in a new window) Try ChatGPT (opens in a new window) Login OpenAI August 7, 2025 Product Introducing GPT‑5 for developers The best model for coding and agentic tasks. Share Introduction Introduction Coding Frontend engineering Co
SWE-Bench Verified resolved rate 21.6
LiveCodeBench pass@1 38.3 across 1055 tasks
ChatGPT Start searching API Dashboard Try ChatGPT Theme Light Dark System Home API Overview Get started with the OpenAI API Models Explore models and compare capabilities Agents Build persistent agents on hosted infrastructure Tools Connect models to tools and data Audio & voice Build speech and realtime voice experiences Production Deploy and scale your API integrations API reference Explore endpoints, parameters, and responses ChatGPT Plugins Extend ChatGPT and Codex Si