GPT-6 Sol Benchmark Details
GPT-6 Sol currently shows benchmark results led by CritPt (6 / 204, score 30.86), Agents' Last Exam (2 / 24, score 56.40), Code Migration (4 / 43, score 57.20). This page also compares it with 2 competitor models and 3 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
Agentic Development
2 evaluationsCode Generation & Editing
3 evaluationsFinance
3 evaluationsLegal
2 evaluationsMedical Reasoning
4 evaluationsService Workflows
2 evaluationsClinical Workflows
2 evaluationsCompetitor Comparison
Benchmark scores for GPT-6 Sol 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-6 SolCurrent | GPT-6 Astra | Claude Opus 5.5 |
|---|---|---|---|
73.10Standard Mode | 83.60Thinking Level · High | 88.40Standard Mode | |
83.15Thinking Level · High ｜ Tools | 87.42Thinking Level · High ｜ Tools | 87.64Thinking Level · High ｜ Tools | |
43.94Thinking Level · High ｜ Tools | 58.18Thinking Level · High ｜ Tools | 66.40Thinking Level · Extra High ｜ Tools | |
68.80Thinking Level · High ｜ Tools | 74.12Thinking Level · Extra High ｜ Tools | -- | |
62.57Standard Mode ｜ Tools | 66.61Thinking Level · High ｜ Tools | 69.69Standard Mode ｜ Tools | |
64.40Thinking Level · High ｜ Tools | 72.60Thinking Level · High ｜ Tools | 81.80Thinking Level · High ｜ Tools | |
56.40Thinking Level · High ｜ Tools | 59.30Thinking Level · High ｜ Tools | -- | |
49.30Thinking Level · High ｜ Tools | 53.30Thinking Level · High ｜ Tools | 54.60Thinking Level · Medium ｜ Tools | |
2.00Thinking Level · High ｜ Tools | -- | 18.50Thinking Level · High ｜ Tools | |
87.82Thinking Level · High ｜ Tools | 89.59Thinking Level · High ｜ Tools | 90.29Thinking Level · High ｜ Tools | |
33.20Thinking Level · Extra High ｜ Tools | 41.40Thinking Level · High ｜ Tools | 40.00Thinking Level · High ｜ Tools | |
30.86Thinking Level · High | 31.70Thinking Level · High | 31.71Thinking Level · High |
Standard API Pricing: GPT-6 Sol 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-6 Sol | OpenAI | $2 / 1M tokens | $10 / 1M tokens | <= 272000 |
GPT-6 Astra | OpenAI | $10 / 1M tokens | $50 / 1M tokens | <= 272000 |
Claude Opus 5.5 | Anthropic | $4 / 1M tokens | $20 / 1M tokens | — |
Version History
How each version of the GPT-6 Sol 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-6 SolCurrent | GPT-5.6 Sol | GPT-5.5 | GPT-5.4 |
|---|---|---|---|---|
73.10Standard Mode | 64.80Thinking Level · Extra High | 69.00Standard Mode | -- | |
83.15Thinking Level · High ｜ Tools | 88.80Thinking Level · High | 83.10Thinking Level · Extra High ｜ Tools | -- | |
43.94Thinking Level · High ｜ Tools | 37.27Thinking Level · High ｜ Tools | 14.60Thinking Level · Extra High ｜ Tools | -- | |
68.80Thinking Level · High ｜ Tools | 72.70Thinking Level · Extra High ｜ Tools | 67.04Thinking Level · Extra High ｜ Tools | 51.77Thinking Level · Extra High ｜ Tools | |
62.57Standard Mode ｜ Tools | 72.63Thinking Level · Extra High | 57.41Thinking Level · Extra High ｜ Tools | -- | |
64.40Thinking Level · High ｜ Tools | 65.70Thinking Level · High | -- | -- | |
56.40Thinking Level · High ｜ Tools | 53.60Thinking Level · High | -- | -- | |
49.30Thinking Level · High ｜ Tools | 47.50Thinking Level · High | -- | -- | |
2.00Thinking Level · High ｜ Tools | 23.00Thinking Level · High ｜ Tools | -- | -- | |
87.82Thinking Level · High ｜ Tools | 80.50Thinking Level · High ｜ Tools | 69.85Thinking Level · Extra High ｜ Tools | 48.47Thinking Level · Extra High ｜ Tools | |
33.20Thinking Level · Extra High ｜ Tools | 45.80Thinking Level · High ｜ Tools | -- | -- | |
30.86Thinking Level · High | 32.30Thinking Level · High | 27.10Thinking Level · Extra High | 23.40Thinking Level · Extra High |
Single-Benchmark Version Trend
Viewing: SimpleBench · Commonsense
Standard API Pricing Across the GPT-6 Sol 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-6 Sol | OpenAI | $2 / 1M tokens | $10 / 1M tokens | <= 272000 |
GPT-5.6 Sol | OpenAI | $4 / 1M tokens | $20 / 1M tokens | — |
GPT-5.5 | OpenAI | $5 / 1M tokens | $30 / 1M tokens | — |
GPT-5.4 | OpenAI | $2.5 / 1M tokens | $15 / 1M tokens | — |