Overall score
71.0
Rank #4 · A confidence
OpenAI · stable
OpenAI's documented flagship API model for complex reasoning and coding workloads.
Overall score
71.0
Rank #4 · A confidence
Capability
65.8
26 eligible benchmark families
Coverage
100%
Confidence A
Benchmarks scored
31
36 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 |
|---|---|---|---|
| BenchLM Math priorRanking weighted | mathematics | 95.3% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 94.6% | 2026-07-15 |
| BrowseCompRanking weighted | agents | 92.2% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 91.9% | 2026-07-15 |
| FrontierMathRanking weighted | mathematics | 89% | 2026-07-15 |
| τ-benchRanking weighted | agents | 85.1% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 85.0877% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 83.41% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 77% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 75.49% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 75.4% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 74.08% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 73.6667% | 2026-07-15 |
| IFBench | instruction following | 72.7% | 2026-07-15 |
| IFEval | instruction following | 72.7% | 2026-07-15 |
| CursorBenchRanking weighted | coding | 67.2% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 65.9091% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 65.9% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 64.6% | 2026-07-15 |
| OSWorldRanking weighted | agents | 62.6% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 62.391% | 2026-07-15 |
| ToolathlonRanking weighted | agents | 58% | 2026-07-15 |
| ITBench-AARanking weighted | agents | 56.2147% | 2026-07-15 |
| SciCodeRanking weighted | coding | 56.1% | 2026-07-15 |
| AA AutomationBenchRanking weighted | agents | 51.2% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 47.2% | 2026-07-16 |
| ExploitGym | agents | 33.7% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 32.9897% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 32.2857% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 21.7 index | 2026-07-15 |
| ARC-AGI-3 | reasoning | 7.8% | 2026-07-15 |
Showing the best of 36 raw result rows across 31 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: value. The last source check for this exact model was 2026-07-14.
Related models
Exact variants remain separate even when they share a provider or family.