Overall score
45.3
Rank #63 · B confidence
OpenAI · stable
GPT-5 is a API model tracked via Artificial Analysis independent evaluations for capability comparison across coding, agents, and reasoning.
Overall score
45.3
Rank #63 · B confidence
Capability
45.5
16 eligible benchmark families
Coverage
72%
Confidence B
Benchmarks scored
16
16 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 |
|---|---|---|---|
| MATH-500 | mathematics | 99.4% | 2026-07-16 |
| AIME 2025 | mathematics | 94.3333% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 85.3535% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 84.7953% | 2026-07-15 |
| LiveCodeBenchRanking weighted | coding | 84.5503% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 75.6% | 2026-07-15 |
| MMMU-ProRanking weighted | multimodal | 74.2197% | 2026-07-15 |
| IFBench | instruction following | 73.0612% | 2026-07-15 |
| SciCodeRanking weighted | coding | 42.9398% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 35.206% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 32.5758% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 28.74% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 26.506% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 19.5876% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 5.7143% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | -8.0833 index | 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.