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), FrontierMath v2 (2 / 58, score 87.72). This page also compares it with 3 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
7 evaluationsCompetitor Comparison
Benchmark scores for GPT-5.5 Pro compared against top models in its class
10 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | GPT-5.5 ProCurrent | Claude Mythos Preview | Gemini 3.1 Pro Preview | Opus 4.7 |
|---|---|---|---|---|
96.50Thinking Level · High | -- | -- | 93.50Thinking Level · High | |
84.60Thinking Level · High | -- | 77.10Thinking Level · High | 75.80Thinking Level · High | |
57.20Thinking Level · Extra High ｜ Tools | 64.70Extended Thinking ｜ Tools | 51.40Thinking Level · High ｜ Tools | 54.70Extended Thinking ｜ Tools | |
93.92Thinking Level · Extra High | 94.60Extended Thinking | 94.30Thinking Level · High | 94.20Extended Thinking | |
76.90Standard Mode | -- | 79.60Standard Mode | 61.70Standard Mode | |
52.40Thinking Level · Extra High ｜ Tools | -- | 36.90Thinking Level · High | 43.80Thinking Level · Extra High | |
39.60Thinking Level · Extra High ｜ Tools | -- | 16.70Standard Mode | 22.90Thinking Level · Extra High | |
78.05Thinking Level · Extra High | -- | -- | 31.71Thinking Level · High | |
87.72Thinking Level · Extra High | -- | -- | 70.18Thinking Level · High | |
90.10Deep Thinking Mode ｜ Tools | 84.90Extended Thinking ｜ Tools | 85.90Thinking Level · High ｜ Tools | 79.30Extended 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
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 | — |
Claude Mythos Preview | Anthropic | $25 / 1M tokens | $125 / 1M tokens | — |
Gemini 3.1 Pro Preview | Google Deep Mind | $2 / 1M tokens | $12 / 1M tokens | <= 200K |
Opus 4.7 | Anthropic | $5 / 1M tokens | $25 / 1M tokens | — |
Version History
How each version of the GPT-5.5 Pro series stacks up on benchmark tests
11 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 |
|---|---|---|---|
96.50Thinking Level · High | 94.50Thinking Level · High | 90.50Thinking Enabled | |
84.60Thinking Level · High | 83.30Thinking Level · High | 54.20Thinking Enabled | |
57.20Thinking Level · Extra High ｜ Tools | 58.70Thinking Level · High ｜ Tools | 50.00Thinking Enabled ｜ Tools | |
93.92Thinking Level · Extra High | 94.60Thinking Level · Extra High | 93.20Thinking Enabled | |
76.90Standard Mode | 74.10Thinking Level · High | 57.40Thinking Level · Extra High | |
52.40Thinking Level · Extra High ｜ Tools | 50.00Thinking Level · Extra High | -- | |
39.60Thinking Level · Extra High ｜ Tools | 38.00Thinking Level · High | 31.30Standard Mode ｜ Tools | |
78.05Thinking Level · Extra High | 58.54Thinking Level · Extra High | 46.00Thinking Level · Extra High | |
87.72Thinking Level · Extra High | 82.46Thinking Level · Extra High | 74.00Thinking Level · Extra High | |
90.10Deep Thinking Mode ｜ Tools | 89.30Thinking Level · High ｜ Tools | 77.90Thinking Level · Extra High ｜ Tools | |
82.30Thinking Level · Extra High | 82.00Thinking Level · High ｜ Tools | -- |
Single-Benchmark Version Trend
Viewing: ARC-AGI-1 · 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
| 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 | — |
GPT-5.2 Pro | OpenAI | $21 / 1M tokens | $168 / 1M tokens | — |
GPT-5.1 Pro | OpenAI | $15 / 1M tokens | $120 / 1M tokens | — |