Overall score
67.2
Rank #8 · A confidence
OpenAI · stable
OpenAI's documented frontier API model with configurable reasoning and a 1.05-million-token context window.
Overall score
67.2
Rank #8 · A confidence
Capability
62.6
35 eligible benchmark families
Coverage
100%
Confidence A
Benchmarks scored
42
58 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 |
|---|---|---|---|
| τ-benchRanking weighted | agents | 93.9% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 93.8596% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 93.6% | 2026-07-15 |
| ARC-AGI-2Ranking weighted | reasoning | 85% | 2026-07-15 |
| BrowseCompRanking weighted | agents | 84.4% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 84.27% | 2026-07-15 |
| CharXivRanking weighted | multimodal | 84.1% | 2026-05-19 |
| BenchLM Knowledge priorRanking weighted | research | 82.2% | 2026-07-15 |
| BenchLM Reasoning priorRanking weighted | reasoning | 81.9% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 81.2% | 2026-05-19 |
| LiveBenchRanking weighted | reasoning | 80.71% | 2026-07-15 |
| OSWorld-VerifiedRanking weighted | agents | 78.7% | 2026-05-19 |
| IFBench | instruction following | 75.9% | 2026-07-15 |
| IFEval | instruction following | 75.9% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 75.3% | 2026-05-19 |
| AA Long Context ReasoningRanking weighted | research | 74.3333% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 71.38% | 2026-07-15 |
| BenchLM Math priorRanking weighted | mathematics | 70.3% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 69.7% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 60.6061% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 60.6% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 58.6% | 2026-05-19 |
| CursorBenchRanking weighted | coding | 58.4% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 58.3% | 2026-07-15 |
| SciCodeRanking weighted | coding | 56.1% | 2026-07-15 |
| ToolathlonRanking weighted | agents | 55.6% | 2026-05-19 |
| Humanity's Last ExamRanking weighted | reasoning | 52.2% | 2026-07-15 |
| Finance Agent v2 | research | 51.8% | 2026-05-19 |
| FrontierMathRanking weighted | mathematics | 51.7% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 49.686% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 46.6428% | 2026-07-15 |
| ITBench-AARanking weighted | agents | 45.8098% | 2026-07-15 |
| AA AutomationBenchRanking weighted | agents | 42.1% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 37.6844% | 2026-07-15 |
| Blueprint-Bench 2 | multimodal | 36.2% | 2026-05-19 |
| ExploitBenchRanking weighted | agents | 34% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 31.3402% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 27.1429% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 20.0667 index | 2026-07-15 |
| ExploitGym | agents | 13.4% | 2026-07-15 |
| OSWorldRanking weighted | agents | 13% | 2026-07-15 |
| Harvey LAB-AARanking weighted | agents | 4.1667% | 2026-07-15 |
Showing the best of 58 raw result rows across 42 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.
Capability ranking is complete for the current snapshot. The last source check for this exact model was 2026-07-15.
Related models
Exact variants remain separate even when they share a provider or family.