Overall score
51.4
Rank #54 · B confidence
OpenAI · stable
OpenAI's GPT-5.4 nano model tracked via the BenchLM July 2026 leaderboard for capability comparison.
Overall score
51.4
Rank #54 · B confidence
Capability
47.9
24 eligible benchmark families
Coverage
72%
Confidence B
Benchmarks scored
30
31 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| GPQA DiamondRanking weighted | reasoning | 82.8% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 76.0234% | 2026-07-15 |
| τ-benchRanking weighted | agents | 76% | 2026-07-15 |
| IFBench | instruction following | 75.9% | 2026-07-15 |
| IFEval | instruction following | 75.9% | 2026-07-15 |
| LiveBenchRanking weighted | reasoning | 70.13% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 67.6% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 66.1% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 66% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 56.1% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 54.2% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 53.9% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 51.6% | 2026-07-15 |
| BenchLM Math priorRanking weighted | mathematics | 49% | 2026-07-15 |
| SciCodeRanking weighted | coding | 46.9% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 42.4242% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 42.4% | 2026-07-15 |
| OSWorld-VerifiedRanking weighted | agents | 39% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 37.7% | 2026-07-15 |
| ToolathlonRanking weighted | agents | 35.5% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 31.4831% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 29.9945% | 2026-07-15 |
| BenchLM Reasoning priorRanking weighted | reasoning | 29.3% | 2026-07-15 |
| FrontierMathRanking weighted | mathematics | 25.86% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 24.9263% | 2026-07-15 |
| ITBench-AARanking weighted | agents | 24.3879% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 21.0309% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 9.2531% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -29.55 index | 2026-07-15 |
| Harvey LAB-AARanking weighted | agents | 0% | 2026-07-15 |
Showing the best of 31 raw result rows across 30 benchmark families.
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: efficiency, value. The last source check for this exact model was 2026-07-16.
Related models
Exact variants remain separate even when they share a provider or family.