Head-to-head · 5 models compared
ChatGPT vs Claude
OpenAI and Anthropic between them account for 5 rated models on the OpenRating Index. ChatGPT's strongest entry is GPT-6 Sol (Max) at 44.0, against Claude's Claude Opus 5 (max) at 44.0. Both are scored on the same axes, with the same tests, below.
Who wins on each axis
ChatGPT leads all three axes in this comparison.
OpenRating Index
ChatGPT
44.0
ChatGPT: GPT-6 Sol (Max) · composite 0–100
Output speed
ChatGPT
204 tok/s
ChatGPT: gpt-oss-120b (High) · blended tok/s, fastest model
Cost / task
ChatGPT
$0.33
ChatGPT: GPT-5.6 Luna (Max) · lowest model, per benchmark run
Every rated model, side by side
Sorted by OpenRating Index. Every figure is measured under the same standardised workload.
| Model | Provider | Index | Reasoning | Speed | Cost / task | Input / 1M |
|---|---|---|---|---|---|---|
| GPT-6 Sol (Max) | ChatGPT | 44.0 | 59.4 | 122 tok/s | $2.47 | $2 |
| Claude Opus 5 (max) | Claude | 44.0 | 59.4 | 79 tok/s | $11.82 | $5 |
| GPT-5.6 Luna (Max) | ChatGPT | 24.0 | 32.4 | 99 tok/s | $0.33 | $0.2 |
| Claude 4.5 Haiku | Claude | 7.0 | 9.5 | 91 tok/s | $0.53 | $1 |
| gpt-oss-120b (High) | ChatGPT | 4.0 | 5.4 | 204 tok/s | $0.35 | $0.15 |
Put ChatGPT and Claude head to head yourself
Pick any combination of models and compare their full cost breakdown — reasoning, answer generation, cache overhead, and input payload — in the OpenRating comparison tool.
Open the comparison tool →