Today's frontier
Claude Fable 5.1 takes the frontier lead
Anthropic edges OpenAI by 2 points on the Artificial Analysis intelligence index.
ModelIntelligence (0–100)
Practical starting points from real OpenRouter usage, production performance, and independent benchmarks.
Practical starting points from real OpenRouter usage, production performance, and independent benchmarks.
Anthropic edges OpenAI by 2 points on the Artificial Analysis intelligence index.
The most capability per dollar of list price.
| Rank | Model | Coding pctl | Tokens | Intel pctl | Agentic pctl |
|---|---|---|---|---|---|
| 1 | 60 | 989.1B | – | – | |
| 2 | 79 | 11.9T | 24 | 68 | |
| 3 | 84 | 12.3T | 55 | 90 | |
| 4 | 65 | 3.2T | – | – | |
| 5 | 84 | 4B | 38 | 74 |
Highest median output speed across multiple providers.
| Rank | Model | Throughput | TTFT p50 | Providers |
|---|---|---|---|---|
| 1 | 790 tok/s | 199ms | 21 | |
| 2 | 478 tok/s | 144ms | 16 | |
| 3 | 380 tok/s | 123ms | 13 | |
| 4 | 293 tok/s | 486ms | 8 | |
| 5 | 287 tok/s | 300ms | 11 |
Pin one model ID and always get the newest release in that family.
| Rank | Model | Family tokens | Context |
|---|---|---|---|
| 1 | 15.8T | 1.1M | |
| 2 | 6.1T | 1M | |
| 3 | 407.8B | 1M | |
| 4 | 12.3T | 1.3M | |
| 5 | 17.5T | 1.3M |
The most-used models with a free endpoint.
| Rank | Model | Tokens/wk | Context |
|---|---|---|---|
| 1 | 5.5T | 1M | |
| 2 | 3.9T | 1M | |
| 3 | 1.4T | 262K | |
| 4 | 1.1T | 1M | |
| 5 | 763.3B | 262K |
Generate videos from text and image prompts across the leading model providers.
Start with a focused set of models for the job you need to do.