Overall score
61.0
Rank #22 · B confidence
OpenAI · stable
OpenAI's API model optimized for agentic coding tasks in Codex and similar environments.
Overall score
61.0
Rank #22 · B confidence
Capability
65.9
18 eligible benchmark families
Coverage
73%
Confidence B
Benchmarks scored
23
24 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 | 91.52% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 91.4% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 89% | 2026-07-15 |
| BenchLM Reasoning priorRanking weighted | reasoning | 87.4% | 2026-07-15 |
| τ-benchRanking weighted | agents | 86% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 85.9649% | 2026-07-15 |
| SWE-bench VerifiedRanking weighted | coding | 85% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 78.5% | 2026-07-15 |
| IFBench | instruction following | 75.4% | 2026-07-15 |
| IFEval | instruction following | 75.4% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 74% | 2026-07-15 |
| LiveBenchRanking weighted | reasoning | 72.76% | 2026-07-15 |
| OSWorld-VerifiedRanking weighted | agents | 64.7% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 64.08% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 61.78% | 2026-07-15 |
| SWE-RebenchRanking weighted | coding | 58.2% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 56.8% | 2026-07-15 |
| SciCodeRanking weighted | coding | 53.2% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 53.0303% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 53% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 39.9% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 16.8571% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 9.8833 index | 2026-07-15 |
Showing the best of 24 raw result rows across 23 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 2026-07-15.
Related models
Exact variants remain separate even when they share a provider or family.