GPT-5.5 Pro Benchmark Details
GPT-5.5 Pro currently shows benchmark results led by FrontierMath - Tier 4 (1 / 80, score 39.60), FrontierMath (1 / 60, score 52.40), ARC-AGI (2 / 68, score 96.50). This page also compares it with 1 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
General Knowledge
6 evaluationsMath and Reasoning
4 evaluationsCompetitor Comparison
Benchmark scores for GPT-5.5 Pro compared against top models in its class
2 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5.5 ProCurrent | Claude Mythos Preview |
|---|---|---|
HLE 综合评估 | 57.20Thinking Level · Extra High ｜ Tools | 64.70Extended Thinking ｜ Tools |
BrowseComp AI Agent - 信息收集 | 90.10Deep Thinking Mode ｜ Tools | 84.90Extended Thinking ｜ Tools |
Standard API Pricing: GPT-5.5 Pro 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
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
GPT-5.5 Pro | OpenAI | $30 / 1M tokens | $180 / 1M tokens | — |
Claude Mythos Preview | Anthropic | $25 / 1M tokens | $125 / 1M tokens | — |
Version History
How each version of the GPT-5.5 Pro series stacks up on benchmark tests
8 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-5.5 ProCurrent | GPT-5.4 Pro | GPT-5.2 Pro |
|---|---|---|---|
ARC-AGI 综合评估 | 96.50Thinking Level · High | 94.50Thinking Level · High | 90.50Thinking Enabled |
ARC-AGI-2 综合评估 | 84.60Thinking Level · High | 83.30Thinking Level · High | 54.20Thinking Enabled |
HLE 综合评估 | 57.20Thinking Level · Extra High ｜ Tools | 58.70Thinking Level · High ｜ Tools | 50.00Thinking Enabled ｜ Tools |
Simple Bench 常识推理 | 76.90Standard Mode | -- | 57.40Thinking Level · Extra High |
FrontierMath 数学推理 | 52.40Thinking Level · Extra High ｜ Tools | 50.00Thinking Level · Extra High | -- |
39.60Thinking Level · Extra High ｜ Tools | 38.00Thinking Level · High | 31.30Thinking Enabled | |
BrowseComp AI Agent - 信息收集 | 90.10Deep Thinking Mode ｜ Tools | 89.30Thinking Level · High ｜ Tools | 77.90Thinking Enabled ｜ Tools |
GDPval-AA 生产力知识 | 82.30Thinking Level · Extra High | 82.00Thinking Level · High ｜ Tools | -- |
Single-Benchmark Version Trend
Viewing: ARC-AGI · 综合评估
Standard API Pricing Across the GPT-5.5 Pro 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
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-5.5 Pro | OpenAI | $30 / 1M tokens | $180 / 1M tokens | — |
GPT-5.4 Pro | OpenAI | $30 / 1M tokens | $180 / 1M tokens | <= 272K |
GPT-5.2 Pro | OpenAI | $21 / 1M tokens | $168 / 1M tokens | — |
GPT-5.1 Pro | OpenAI | $15 / 1M tokens | $120 / 1M tokens | — |