Overall score
57.2
Rank #32 · B confidence
OpenAI · stable
OpenAI's GPT-5.1 model tracked via the BenchLM July 2026 leaderboard for capability comparison.
Overall score
57.2
Rank #32 · B confidence
Capability
54.6
13 eligible benchmark families
Coverage
49%
Confidence B
Benchmarks scored
19
19 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 Multimodal priorRanking weighted | multimodal | 91.8% | 2026-07-15 |
| τ-benchRanking weighted | agents | 81.9% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 81.8713% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 76.9% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 75% | 2026-07-15 |
| IFBench | instruction following | 72.9% | 2026-07-15 |
| IFEval | instruction following | 72.9% | 2026-07-15 |
| BenchLM Reasoning priorRanking weighted | reasoning | 65.4% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 56.85% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 51.03% | 2026-07-15 |
| BenchLM Math priorRanking weighted | mathematics | 47.4% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 45.5% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 45.4545% | 2026-07-15 |
| SciCodeRanking weighted | coding | 43.3% | 2026-07-15 |
| FrontierMathRanking weighted | mathematics | 31.034% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 24.3725% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 14.0206% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 5.55 index | 2026-07-15 |
| CritPtRanking weighted | reasoning | 4.8571% | 2026-07-15 |
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 2026-07-15.
Related models
Exact variants remain separate even when they share a provider or family.