Benchmarks / Microsoft STATE-Bench
Mean rating of the conversation from the simulated user's side.
Data older than 90 days: last updated 1 Jul 2026
4 results · score from 1 to 5, higher is better. Choose a model to highlight it.Clear highlight
| # | Model | User experience score from 1 to 5, higher is better | Price $ per million tokens, in / out |
|---|---|---|---|
| 1 | GPT-5.4 (high reasoning)OpenAI · best of 2 settings |
3.49
|
$2.50 / $15 |
| 2 | Claude Opus 4.7 (high reasoning)Anthropic |
3.46
|
$5 / $25 |
| 3 | Kimi K2.6Moonshot AI |
3.37
|
$0.95 / $4 |
| 4 | DeepSeek-V4-Pro (0423)DeepSeek |
3.36
|
$1.42 / $2.83 |
Swipe the table sideways for more columns.
Ranks follow the score as shown, so equal numbers share a rank. Each model is shown at its best setting; show every setting. Results as published by Microsoft STATE-Bench; we do not re-run them.
User experience, plotted at each model's release date, higher is better. Each model counts once, at its best setting. Scores are today's, not launch day's. Hover or tap a mark for its model.
Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.
Each lab's best so far, stepping whenever one of its releases beats its own earlier models.
OpenAIAnthropicMoonshot AIDeepSeek
Mean rating of the conversation from the simulated user's side.
Not real customer satisfaction: the ratings come from a model-based judge.
We rank a result only when we can tie it to a specific model you can use. These are left out:
STATE-Bench by Microsoft and STATE-Bench contributors, MIT License.