LLM Leaderboard
What teams run on the Respan gateway, how models score on the Respan Index, what they cost, and whether their providers are up.
Top models
The models processing the most tokens through Respan, tracked weekly.
What teams run on the Respan gateway, how models score on the Respan Index, what they cost, and whether their providers are up.
The models processing the most tokens through Respan, tracked weekly.
The providers handling the most routed traffic through Respan, tracked weekly.
The models accounting for the most gateway spend, tracked weekly.
The models handling the most gateway requests, tracked weekly.
The models gaining and losing gateway traffic fastest, week over week.
GPT-6.1 Sol
by openai
237B tokens
NEW
Gemini 3.5 Flash Lite
by google
1.86B tokens
↑151%
Gemini 3 Flash
by google
1.45B tokens
↑126%
Claude Haiku 4.5
by anthropic
4.31B tokens
↑120%
GPT-6 Luna
by openai
282B tokens
↑94%
Span 01 Free
by respan
3.82B tokens
↓84%
GPT-4.1 Nano
by openai
1.77B tokens
↓83%
GPT-5.6 Luna
by openai
892B tokens
↓82%
Claude Opus 4.8
by anthropic
38.8B tokens
↓80%
GPT-5.4 Nano
by openai
1.35B tokens
↓78%
Models ranked on one 0 to 100 score from public benchmarks and lab results.
| Model | Respan Index | $ in / out | Context | |
|---|---|---|---|---|
| 1. | Claude Opus 5.5by Anthropic | 72.7 | $4 / $20 | 1M |
| 2. | Gemini 4 Argonby Google | 71.4 | $2 / $10 | - |
| 3. | GPT-6 Astraby OpenAI | 70.7 | $10 / $50 | 1.1M |
| 4. | GPT-6.1 Solby OpenAI | 69.7 | $2 / $10 | 1.1M |
| 5. | Claude Fable 5.1by Anthropic | 69.2 | $10 / $50 | 1M |
List prices per 1M tokens. * Estimated, no published scores in that category.
Respan Index against blended price per 1M tokens (3 input to 1 output), cheapest on the right.
Best value models, best score first:
The top three for each task, from the Respan Index and list prices.
Llama 4 Scout
by Meta
10M tokens
Index 8.8
Grok 4.1 Fast Reasoning
by xAI
2M tokens
Index 20.7
Grok 4 Fast Reasoning
by xAI
2M tokens
Index 18.0
Compare families:Claude vs GeminiClaude vs GrokClaude vs GPTGemini vs GPTGemini vs GrokClaude vs DeepSeekClaude vs KimiDeepSeek vs Qwen
Live status from each provider's official status page, every five minutes.
Minor incidents show on the bars but don't lower uptime. Data from llmmetric.com.
62 public benchmarks, combined into one score for 143 models.
Version 1.1, 2,629 cited results from llmmetric, Respan's benchmark database.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.
Use Respan with your favorite frameworks and tools.
