GPT-6 Luna Benchmark Details
GPT-6 Luna currently shows benchmark results led by AA-LCR (15 / 174, score 83), Agents' Last Exam (5 / 24, score 50.90), CritPt (43 / 204, score 19). This page also compares it with 3 competitor models and 2 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
General Knowledge
7 evaluationsAI Agent - Tool Usage
5 evaluationsCoding and Software Engineer
7 evaluationsProductivity Knowledge
12 evaluationsOther
5 evaluationsCompetitor Comparison
Benchmark scores for GPT-6 Luna 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 LunaCurrent | DeepSeek-V4.1-Flash | GLM-5.3-Flash | Claude Sonnet 5 |
|---|---|---|---|---|
37.00Standard Mode ｜ Tools | 39.50Standard Mode ｜ Tools | 41.90Thinking Level · High | 38.40Standard Mode ｜ Tools | |
19.00Thinking Level · High | 14.30Thinking Level · High | 15.40Thinking Enabled | 16.90Thinking Level · High | |
39.00Thinking Level · High | 63.90Thinking Level · High ｜ Tools | 55.30Thinking Level · High ｜ Tools | 57.40Thinking Level · Extra High ｜ Tools | |
83.00Thinking Level · High | 84.00Thinking Level · High | -- | 82.00Thinking Level · High | |
53.00Thinking Level · High ｜ Tools | 68.90Thinking Level · High | 60.40Thinking Level · High | -- | |
73.03Thinking Level · High ｜ Tools | 90.60Thinking Level · High ｜ Tools | 84.30Thinking Level · High ｜ Tools | 80.50Thinking Level · High ｜ Tools | |
13.00Thinking Level · High ｜ Tools | 26.80Thinking Level · High ｜ Tools | 32.80Thinking Enabled ｜ Tools | 12.42Thinking Level · High ｜ Tools | |
66.60Thinking Level · High ｜ Tools | 74.20Thinking Level · High ｜ Tools | 63.39Thinking Level · High ｜ Tools | 54.00Deep Thinking Mode ｜ Tools | |
0.50Thinking Level · High ｜ Tools | 20.30Thinking Level · High ｜ Tools | -- | -- | |
55.00Thinking Level · High | 51.90Thinking Level · High | 51.60Thinking Enabled | 54.30Thinking Level · High | |
50.90Thinking Level · High ｜ Tools | 31.80Thinking Level · High ｜ Tools | 26.30Thinking Level · High ｜ Tools | -- | |
1299.00Thinking Level · High ｜ Tools | 1424.00Thinking Level · High ｜ Tools | -- | 1355.00Thinking Level · High ｜ Tools |
Standard API Pricing: GPT-6 Luna 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 Luna | OpenAI | $0.1 / 1M tokens | $0.5 / 1M tokens | <= 272000 |
GLM-5.3-Flash | 智谱AI | $0.075 / 1M tokens | $0.25 / 1M tokens | — |
Claude Sonnet 5 | Anthropic | $2 / 1M tokens | $10 / 1M tokens | — |
Version History
How each version of the GPT-6 Luna 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 LunaCurrent | GPT-5.6 Luna | GPT-5.4 mini |
|---|---|---|---|
37.00Standard Mode ｜ Tools | 37.50Standard Mode ｜ Tools | -- | |
86.70Thinking Level · High | 88.00Thinking Level · High | 63.67Thinking Level · Extra High ｜ Tools | |
59.30Thinking Level · High | 59.54Thinking Level · High | 18.90Thinking Level · Extra High ｜ Tools | |
0.19Thinking Level · Medium | 0.20Thinking Level · High | -- | |
19.00Thinking Level · High | 20.60Thinking Level · Extra High | 10.00Thinking Level · Extra High | |
39.00Thinking Level · High | 39.50Thinking Level · High | 41.50Thinking Level · Extra High ｜ Tools | |
83.00Thinking Level · High | 83.70Thinking Level · High | 77.00Thinking Level · Extra High | |
73.03Thinking Level · High ｜ Tools | 84.70Thinking Level · High | 59.20Thinking Level · Extra High ｜ Tools | |
13.00Thinking Level · High ｜ Tools | 17.27Thinking Level · High ｜ Tools | 2.00Thinking Level · Extra High ｜ Tools | |
66.60Thinking Level · High ｜ Tools | 67.20Thinking Level · Extra High ｜ Tools | -- | |
55.00Thinking Level · High | 53.60Thinking Level · High | 52.10Thinking Level · Extra High | |
50.90Thinking Level · High ｜ Tools | 50.30Thinking Level · Extra High ｜ Tools | -- |
Single-Benchmark Version Trend
Viewing: AA Intelligence Index v4.3 · 综合评估
Standard API Pricing Across the GPT-6 Luna 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 Luna | OpenAI | $0.1 / 1M tokens | $0.5 / 1M tokens | <= 272000 |
GPT-5.6 Luna | OpenAI | $0.2 / 1M tokens | $1.2 / 1M tokens | — |
GPT-5.4 mini | OpenAI | $0.75 / 1M tokens | $4.5 / 1M tokens | — |