GPT-5 Benchmark Details
GPT-5 currently shows benchmark results led by Aider-Polyglot (1 / 59, score 88), AIME2025 (10 / 215, score 99.60), Fiction.liveBench (1 / 16, score 97.20). This page also compares it with 2 competitor models and 3 predecessor or same-series models, including performance and pricing views when available. 1 source link is attached for reference.
Benchmark Results
Benchmark Results
Abstract Generalization
8 evaluationsKnowledge Exams
9 evaluationsScientific Reasoning
7 evaluationsRepository Engineering
2 evaluationsAlgorithmic Coding
7 evaluationsMathematics
18 evaluationsAgentic Development
9 evaluationsVisual Understanding
11 evaluationsService Workflows
8 evaluationsInstruction Following
4 evaluationsLong Reasoning
3 evaluationsCapability Frontier Metrics
2 evaluationsCode Generation & Editing
1 evaluationsClinical Workflows
2 evaluationsCompetitor Comparison
Benchmark scores for GPT-5 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5Current | Claude Opus 4 | Gemini 2.5-Pro |
|---|---|---|---|
65.67Thinking Level · High | 35.67Standard Mode | 37.00Thinking Enabled | |
9.86Thinking Level · High | 8.61Standard Mode | 4.86Thinking Enabled | |
35.20Thinking Enabled ｜ Tools | 12.30Thinking Enabled | 22.50Thinking Enabled | |
5.70Thinking Level · High | -- | 2.60Thinking Enabled | |
87.30Thinking Enabled ｜ Tools | 79.60Standard Mode | 86.40Thinking Enabled | |
72.80Thinking Level · High | 72.50Standard Mode | 67.20Thinking Enabled | |
1360.00Standard Mode ｜ Tools | -- | 1125.00Standard Mode ｜ Tools | |
11.00Thinking Enabled ｜ Tools | -- | 19.00Thinking Enabled ｜ Tools | |
29.00Thinking Enabled ｜ Tools | -- | 15.20Thinking Enabled ｜ Tools | |
84.60Thinking Level · High | 63.60Thinking Enabled | 80.10Thinking Enabled | |
99.60Thinking Enabled ｜ Tools | 75.50Standard Mode | 88.00Thinking Enabled | |
26.30Thinking Level · High ｜ Tools | 4.50Standard Mode | 11.00Standard Mode |
Standard API Pricing: GPT-5 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
When a context threshold exists, the charted base price only applies within these limits:
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GPT-5 | OpenAI | $1.25 / 1M tokens | $10 / 1M tokens | — |
Claude Opus 4 | Anthropic | $15 / 1M tokens | $75 / 1M tokens | — |
Gemini 2.5-Pro | Google DeepMind | $1.25 / 1M tokens | $10 / 1M tokens | <= 200000 |
Version History
How each version of the GPT-5 series stacks up on benchmark tests
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | GPT-5Current | GPT-4.5 | GPT-4.1 | GPT-4o(2025-03-27) |
|---|---|---|---|---|
65.67Thinking Level · High | -- | -- | 8.80Standard Mode | |
35.20Thinking Enabled ｜ Tools | 5.44Standard Mode | 5.40Thinking Level · High | -- | |
87.30Thinking Enabled ｜ Tools | 71.40Standard Mode | 66.30Standard Mode | 66.90Standard Mode | |
72.80Thinking Level · High | 38.00Standard Mode | 54.60Standard Mode | -- | |
84.60Thinking Level · High | 46.40Standard Mode | 40.50Standard Mode | 35.80Standard Mode | |
99.60Thinking Enabled ｜ Tools | -- | 36.70Standard Mode | 26.70Standard Mode | |
26.30Thinking Level · High ｜ Tools | -- | 5.50Standard Mode | -- | |
1623.50Standard Mode | 1255.30Standard Mode | 1417.20Standard Mode | 1502.10Standard Mode | |
88.00Thinking Level · High | 44.90Standard Mode | 52.40Standard Mode | 45.30Standard Mode | |
37.90Thinking Level · Medium ｜ Tools | -- | 13.60Standard Mode ｜ Tools | -- | |
81.00Thinking Level · Medium | -- | 72.00Standard Mode | -- | |
84.20Thinking Level · High | 74.40Thinking Level · High | -- | -- |
Single-Benchmark Version Trend
Viewing: ARC-AGI-1 · Abstract Generalization
Standard API Pricing Across the GPT-5 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GPT-5 | OpenAI | $1.25 / 1M tokens | $10 / 1M tokens | — |
GPT-4.1 | Microsoft Azure | $2 / 1M tokens | $8 / 1M tokens | — |
GPT-4o(2025-03-27) | OpenAI | $2.5 / 1M tokens | $10 / 1M tokens | — |