Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
OpenAI · Proprietary · rank 121 · bench-align-v5
GPT-5.4 nano is built for coding. It ranks in the top quarter for instruction following (top 7% of 159 scored models) and coding (top 15% of 210 scored models), by BenchLM's published scores. It accepts text and images and produces text.
GPT-5.4 nano by OpenAI scores 44.5 overall, costs $0.20 per 1M input tokens and $1.25 per 1M output tokens, and carries a context window of 400K tokens — observed 2026-11-21.
Every published price component, including cache reads and writes.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Lifecycle events the source associates with this model, plus what this profile does not claim.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 3.64 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 191 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Plans from the model's maker, and the API providers that list this exact model today. Links leave ModelScale; each provider sets its own prices and limits.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 82.8 | #66 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| HLE Humanity's Last Exam | 37.7 | #41 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 20.7 | #110 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 81.7 | #97 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 28.3 | #94 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | -29.5 | #144 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 25.7 | #114 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 74.2 | #102 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HLE w/o tools Humanity's Last Exam without tools | 24.3 | #51 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 77.5 | #67 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 77.2 | #81 | Academic multiple-choice questions | Broad academic knowledge | Vals AI MMLU-Pro, Vals AI run leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 46.3 | #56 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| Vibe Code Bench Vibe Code Bench v1.1 | 26.10 | #20 | End-to-end web application builds | End-to-end software delivery | Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development |
| AA Coding Index Artificial Analysis Coding Index | 56.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 44.912 | #50 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 12.195 | #53 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ARC-AGI-1 ARC-AGI-1 Semi-Private Evaluation | 51.50 | #43 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | ARC Prize leaderboard |
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 5.7 | #50 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | ARC-AGI-2: A Harder General Intelligence Benchmark |
| AA-LCR Artificial Analysis Long Context Reasoning | 76.7 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-IFBench Artificial Analysis IFBench | 75.9 | #17 | Verifiable instruction constraints | Instruction precision | Artificial Analysis IFBench Benchmark Leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 46.3 | #59 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| GDPval-AA GDPval-AA | 1035 | #85 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 22.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 66.1 | #50 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 65.4 | #85 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| MMMU-Pro w/ Python MMMU-Pro with Python | 69.5 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 45.0 | #28 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 5.0 | #76 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
People's votes between two anonymous answers on arena.ai, one board per task. LMArena's own ratings and ranks, one line per model version it rates; not part of this site's capability scores or rank.
| Board | Variant | Rating | Votes | Rank | Published | Evidence |
|---|---|---|---|---|---|---|
| Vision Arena People's votes between two answers about the same image, style-controlled. | High | 1,199 ± 6 | 25,347 | 96 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #45 |
| Cross-benchmark coding index |
| Display-only external reference |
| Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 47.2 | #67 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 84.0 | #40 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 69.8 | #58 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| #89 |
| Long-context reasoning tasks |
| Long-context reasoning |
| Artificial Analysis model benchmarks |
| CritPt Critical Physics Tasks | 9.3 | #72 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
| #81 |
| Economically valuable tasks |
| Professional agentic workflows |
| Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 17.7 | #47 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| APEX-Agents-AA APEX-Agents-AA | 24.9 | #18 | 452 professional-services agent tasks | Long-horizon workplace agent tasks | APEX-Agents-AA Benchmark Leaderboard |
| OSWorld-Verified OSWorld-Verified | 39 | #38 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | OSWorld |
| MCP Atlas MCP Atlas | 56.1 | #43 | Tool-integrated agent tasks | Advanced tool use | Introducing GPT-5.4 mini and nano |
| Toolathlon Toolathlon | 35.5 | #21 | Multi-tool workflows | Advanced tool use | Introducing GPT-5.4 mini and nano |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 92.5 | #35 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 41.6 | #64 | Difficult terminal tasks | Frontier agentic | Vals AI Terminal-Bench 2.1, Vals AI run leaderboard |
| #10 |
| Multimodal academic reasoning |
| Frontier multimodal |
| Introducing GPT-5.4 mini and nano |
| ParseBench-1 ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release) | 42.24 | #37 | 2,078 human-verified enterprise pages from insurance, finance and government documents | No method is strong on all five dimensions; charts and visual grounding separate the field | ParseBench: A Document Parsing Benchmark for AI Agents |
| ExtractBench (LlamaIndex) ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard) | 74.90 | #24 | 370 documents, 4,869 pages, 8 business domains, 67 document types, each with a JSON Schema | Short documents are near solved; long record lists and grounding separate systems | ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction |