Quality
Highest overall scores
- 1
OpenAI: GPT-5.6 Sol60.9 - 2OpenAI: GPT-5.6 Terra56.6
- 3OpenAI: GPT-5.6 Luna52.3
OpenAI model benchmarks.
Compare OpenAI models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1OpenAI: GPT-5.6 Luna139 t/s
- 2OpenAI: GPT-5.6 Luna Pro136 t/s
- 3OpenAI: GPT-5.6 Terra Pro119 t/s
Input price
Lowest price per 1M tokens
- 1OpenAI: GPT-5.6 Luna$0.10/1M
- 2OpenAI: GPT-5.6 Luna Pro$0.10/1M
- 3OpenAI GPT Mini Latest$0.75/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare OpenAI model capability.
Performance and price
Compare practical tradeoffs.
All OpenAI models.
8 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| OpenAI: GPT-5.6 Sol | 60.9 | 44 t/s | 1.1M | $5.00 | $30.00 | |
| OpenAI: GPT-5.6 Terra | 56.6 | 104 t/s | 1.1M | $1.00 | $6.00 | |
| OpenAI: GPT-5.6 Luna | 52.3 | 139 t/s | 1.1M | $0.10 | $0.60 | |
| OpenAI GPT Mini Latest | 0 | — | 400K | $0.75 | $4.50 | |
| OpenAI: GPT Chat Latest | 0 | 42 t/s | 400K | $5.00 | $30.00 | |
| OpenAI: GPT-5.6 Luna Pro | 0 | 136 t/s | 1.1M | $0.10 | $0.60 | |
| OpenAI: GPT-5.6 Sol Pro | 0 | 80 t/s | 1.1M | $5.00 | $30.00 | |
| OpenAI: GPT-5.6 Terra Pro | 0 | 119 t/s | 1.1M | $1.00 | $6.00 |
OpenAI technical benchmarks.
Compare named evaluation records available for OpenAI models. Missing results remain blank rather than being estimated.
| Benchmark | Area | GPT-5.6 Sol | GPT-5.6 Terra | GPT-5.6 Luna | OpenAI GPT Mini Latest | GPT Chat Latest | GPT-5.6 Luna Pro | GPT-5.6 Sol Pro | GPT-5.6 Terra Pro | Source |
|---|---|---|---|---|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 60.9 | 56.6 | 52.3 | — | — | — | — | — | OpenRouter / artificial-analysis |
| Coding Index | coding | 77.4 | 76.7 | 71.4 | — | — | — | — | — | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 57.8 | 50.2 | 46.9 | — | — | — | — | — | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 94.1 | 92.5 | 91.1 | — | — | — | — | — | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 49.5 | 42.9 | 39.5 | — | — | — | — | — | OpenRouter model benchmarks |
| IFBench | IFBench | 72.7 | 71.2 | — | — | — | — | — | — | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 85.1 | 86.3 | — | — | — | — | — | — | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 77.7 | 79.7 | 78.3 | — | — | — | — | — | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 61.4 | 53.9 | 54 | — | — | — | — | — | OpenRouter model benchmarks |
| CritPt | CritPt | 32.3 | 30 | 20.6 | — | — | — | — | — | OpenRouter model benchmarks |
| SciCode | SciCode | 56.1 | 53.9 | 52.5 | — | — | — | — | — | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 65.9 | 57.6 | — | — | — | — | — | — | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 59.4 | 46.8 | 42.7 | — | — | — | — | — | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 7.8 | 12.1 | 7.4 | — | — | — | — | — | OpenRouter model benchmarks |
OpenAI image models.
| Model | Quality | Evidence | Price /1k images | Links |
|---|---|---|---|---|
| GPT Image 2 | 1340 Elo | 21,398 samples | $211 | View details |
| GPT Image 1 | — | — | — | View details |
| GPT Image 1 Mini | — | — | — | View details |
| GPT-5 Image | — | — | — | View details |
| GPT-5 Image Mini | — | — | — | View details |
| GPT-5.4 Image 2 | — | — | — | View details |
OpenAI video models.
| Model | Quality | Text to video | Image to video | Links |
|---|---|---|---|---|
| Sora 2 Pro | — | — | — | View details |