# τ-bench Verified (airline): AI model scores

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/benchmark/tau-bench-airline/
- **Idioma:** en
- **Atualizado:** 2026-11-17

---
AI models

# τ-bench Verified (airline): AI model scores

130 AI models on τ-bench Verified (airline), per OpenRouter Benchmarks. Low discrimination: most models tie with the top score.

τ-bench Verified (airline), on the OpenRouter Benchmarks leaderboard (CC BY 4.0, latest version we checked), simulates an airline support agent that uses systems and must follow company policy until the end of the conversation. The score is the share of tasks completed within the rules. Here are the 130 models in this section with a score on τ-bench Verified (airline), per OpenRouter Benchmarks. Most are in a statistical tie with the top score, so the table shows the score without a rank or a badge.

τ-bench Verified (airline)

82%

Claude Fable 5

models

130

| Model | % | Source |
| --- | --- | --- |
| [Claude Fable 5](https://meirinho.com.br/en/ia/modelos/claude-fable-5/)Anthropic · closed | 82% | OpenRouter Benchmarks |
| [DeepSeek V4 Flash 0423](https://meirinho.com.br/en/ia/modelos/deepseek-v4-flash/)DeepSeek · open | 81.7% | OpenRouter Benchmarks |
| [Gemini 3.7 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-7-flash/)Google · closed | 80.7% | OpenRouter Benchmarks |
| [Qwen3.5 397B A17B](https://meirinho.com.br/en/ia/modelos/qwen3-5-397b-a17b/)Alibaba · open | 80.2% | OpenRouter Benchmarks |
| [GPT-5.1](https://meirinho.com.br/en/ia/modelos/gpt-5-1/)OpenAI · closed | 80% | OpenRouter Benchmarks |
| [Ling 3.1 Flash](https://meirinho.com.br/en/ia/modelos/ling-3-1-flash/)Ant Group · undisclosed | 79.3% | OpenRouter Benchmarks |
| [Claude Fable 5.1](https://meirinho.com.br/en/ia/modelos/claude-fable-5-1/)Anthropic · closed | 79.2% | OpenRouter Benchmarks |
| [Qwen3.6 27B](https://meirinho.com.br/en/ia/modelos/qwen3-6-27b/)Alibaba · open | 79% | OpenRouter Benchmarks |
| [MiMo V2.6 Pro](https://meirinho.com.br/en/ia/modelos/mimo-v2-6-pro/)Xiaomi · open | 78.9% | OpenRouter Benchmarks |
| [Claude Sonnet 5.5](https://meirinho.com.br/en/ia/modelos/claude-sonnet-5-5/)Anthropic · closed | 78.8% | OpenRouter Benchmarks |
| [GLM-5.3](https://meirinho.com.br/en/ia/modelos/glm-5-3/)Zhipu AI (Z.ai) · open | 78.8% | OpenRouter Benchmarks |
| [Claude Opus 5](https://meirinho.com.br/en/ia/modelos/claude-opus-5/)Anthropic · closed | 78.7% | OpenRouter Benchmarks |
| [Gemini 4 Argon](https://meirinho.com.br/en/ia/modelos/gemini-4-argon/)Google · closed | 78.7% | OpenRouter Benchmarks |
| [Kimi K3.1 Pro](https://meirinho.com.br/en/ia/modelos/kimi-k3-1-pro/)Moonshot AI · open | 78.7% | OpenRouter Benchmarks |
| [Qwen3.5-35B-A3B](https://meirinho.com.br/en/ia/modelos/qwen3-5-35b-a3b/)Alibaba · open | 78.7% | OpenRouter Benchmarks |
| [DeepSeek V4 Pro](https://meirinho.com.br/en/ia/modelos/deepseek-v4-pro/)DeepSeek · open | 78.6% | OpenRouter Benchmarks |
| [Gemini 3.5 Flash Lite](https://meirinho.com.br/en/ia/modelos/gemini-3-5-flash-lite/)Google · closed | 78.3% | OpenRouter Benchmarks |
| [MiMo-V2.6-Flash](https://meirinho.com.br/en/ia/modelos/mimo-v2-6-flash/)Xiaomi · open | 78.2% | OpenRouter Benchmarks |
| [Qwen3.8 27B](https://meirinho.com.br/en/ia/modelos/qwen3-8-27b/)Alibaba · open | 78% | OpenRouter Benchmarks |
| [Claude Opus 4.7](https://meirinho.com.br/en/ia/modelos/claude-opus-4-7/)Anthropic · closed | 77.8% | OpenRouter Benchmarks |
| [DeepSeek V4.1 Flash](https://meirinho.com.br/en/ia/modelos/deepseek-v4-1-flash/)DeepSeek · open | 77.8% | OpenRouter Benchmarks |
| [Qwen3.5-122B-A10B](https://meirinho.com.br/en/ia/modelos/qwen3-5-122b-a10b/)Alibaba · open | 77.7% | OpenRouter Benchmarks |
| [Hy4](https://meirinho.com.br/en/ia/modelos/hy4/)Tencent · open | 77.6% | OpenRouter Benchmarks |
| [Claude Opus 4.8](https://meirinho.com.br/en/ia/modelos/claude-opus-4-8/)Anthropic · closed | 77.5% | OpenRouter Benchmarks |
| [Qwen3.8 2.4T A95B](https://meirinho.com.br/en/ia/modelos/qwen3-8-2-4t-a95b/)Alibaba · open | 77.4% | OpenRouter Benchmarks |
| [Kimi K2.7 Code](https://meirinho.com.br/en/ia/modelos/kimi-k2-7-code/)Moonshot AI · open | 77.3% | OpenRouter Benchmarks |
| [Muse Glimmer 30B](https://meirinho.com.br/en/ia/modelos/muse-glimmer-30b/)Meta · open | 77.2% | OpenRouter Benchmarks |
| [Gemini 3.1 Pro](https://meirinho.com.br/en/ia/modelos/gemini-3-1-pro/)Google · closed | 77% | OpenRouter Benchmarks |
| [Gemma 4 31B](https://meirinho.com.br/en/ia/modelos/gemma-4-31b/)Google · open | 77% | OpenRouter Benchmarks |
| [GLM 5](https://meirinho.com.br/en/ia/modelos/glm-5/)Zhipu AI (Z.ai) · open | 76.9% | OpenRouter Benchmarks |
| [DeepSeek V4 Flash Vision Exp](https://meirinho.com.br/en/ia/modelos/deepseek-v4-flash-vision-exp/)DeepSeek · open | 76.7% | OpenRouter Benchmarks |
| [Gemini 3.8 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-8-flash/)Google · closed | 76.7% | OpenRouter Benchmarks |
| [GLM-5.2](https://meirinho.com.br/en/ia/modelos/glm-5-2/)Zhipu AI (Z.ai) · open | 76.7% | OpenRouter Benchmarks |
| [Nova Micro 1.0](https://meirinho.com.br/en/ia/modelos/nova-micro-v1/)Amazon · undisclosed | 76.7% | OpenRouter Benchmarks |
| [Claude Opus 4.5](https://meirinho.com.br/en/ia/modelos/claude-opus-4-5/)Anthropic · closed | 76.6% | OpenRouter Benchmarks |
| [Qwen3.8 Flash](https://meirinho.com.br/en/ia/modelos/qwen3-8-flash/)Alibaba · open | 76.4% | OpenRouter Benchmarks |
| [Gemini 3.6 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-6-flash/)Google · closed | 76.3% | OpenRouter Benchmarks |
| [GLM-5.3-Flash](https://meirinho.com.br/en/ia/modelos/glm-5-3-flash/)Zhipu AI (Z.ai) · open | 76.3% | OpenRouter Benchmarks |
| [MiniMax M3](https://meirinho.com.br/en/ia/modelos/minimax-m3/)MiniMax · open | 76.3% | OpenRouter Benchmarks |
| [Kimi K3](https://meirinho.com.br/en/ia/modelos/kimi-k3/)Moonshot AI · open | 76.2% | OpenRouter Benchmarks |
| [Qwen3.6 35B A3B](https://meirinho.com.br/en/ia/modelos/qwen3-6-35b-a3b/)Alibaba · open | 76.2% | OpenRouter Benchmarks |
| [GLM 4.7](https://meirinho.com.br/en/ia/modelos/glm-4-7/)Zhipu AI (Z.ai) · open | 76% | OpenRouter Benchmarks |
| [Claude Opus 4.6](https://meirinho.com.br/en/ia/modelos/claude-opus-4-6/)Anthropic · closed | 75.8% | OpenRouter Benchmarks |
| [GLM 5.1](https://meirinho.com.br/en/ia/modelos/glm-5-1/)Zhipu AI (Z.ai) · open | 75.8% | OpenRouter Benchmarks |
| [Muse Spark Open](https://meirinho.com.br/en/ia/modelos/muse-spark-open/)Meta · open | 75.7% | OpenRouter Benchmarks |
| [Qwen3.5-9B](https://meirinho.com.br/en/ia/modelos/qwen3-5-9b/)Alibaba · open | 75.7% | OpenRouter Benchmarks |
| [Claude Sonnet 5](https://meirinho.com.br/en/ia/modelos/claude-sonnet-5/)Anthropic · closed | 75.4% | OpenRouter Benchmarks |
| [Claude Opus 5.5](https://meirinho.com.br/en/ia/modelos/claude-opus-5-5/)Anthropic · closed | 75.3% | OpenRouter Benchmarks |
| [GPT-5.3-Codex](https://meirinho.com.br/en/ia/modelos/gpt-5-3-codex/)OpenAI · closed | 75.3% | OpenRouter Benchmarks |
| [Grok 4.6](https://meirinho.com.br/en/ia/modelos/grok-4-6/)xAI · closed | 75.3% | OpenRouter Benchmarks |
| [Grok 4.7](https://meirinho.com.br/en/ia/modelos/grok-4-7/)xAI · closed | 75.3% | OpenRouter Benchmarks |
| [GPT-5.4](https://meirinho.com.br/en/ia/modelos/gpt-5-4/)OpenAI · closed | 75% | OpenRouter Benchmarks |
| [Claude Sonnet 4.5](https://meirinho.com.br/en/ia/modelos/claude-sonnet-4-5/)Anthropic · closed | 74.9% | OpenRouter Benchmarks |
| [Kimi K2.6](https://meirinho.com.br/en/ia/modelos/kimi-k2-6/)Moonshot AI · open | 74.9% | OpenRouter Benchmarks |
| [Nemotron 3.5 Super VL](https://meirinho.com.br/en/ia/modelos/nemotron-3-5-super-vl/)NVIDIA · open | 74.9% | OpenRouter Benchmarks |
| [Claude Sonnet 4.6](https://meirinho.com.br/en/ia/modelos/claude-sonnet-4-6/)Anthropic · closed | 74.8% | OpenRouter Benchmarks |
| [DeepSeek V3.2](https://meirinho.com.br/en/ia/modelos/deepseek-v3-2/)DeepSeek · open | 74.7% | OpenRouter Benchmarks |
| [GPT-5.5](https://meirinho.com.br/en/ia/modelos/gpt-5-5/)OpenAI · closed | 74.7% | OpenRouter Benchmarks |
| [MiMo-V2.5](https://meirinho.com.br/en/ia/modelos/mimo-v2-5/)Xiaomi · open | 74.7% | OpenRouter Benchmarks |
| [MiniMax M3.1 Flash](https://meirinho.com.br/en/ia/modelos/minimax-m3-1-flash/)MiniMax · open | 74.7% | OpenRouter Benchmarks |
| [GPT-5.6 Sol](https://meirinho.com.br/en/ia/modelos/gpt-5-6-sol/)OpenAI · closed | 74.2% | OpenRouter Benchmarks |
| [MiMo-V2.5-Pro](https://meirinho.com.br/en/ia/modelos/mimo-v2-5-pro/)Xiaomi · open | 74.1% | OpenRouter Benchmarks |
| [Claude Haiku 5.5](https://meirinho.com.br/en/ia/modelos/claude-haiku-5-5/)Anthropic · closed | 74% | OpenRouter Benchmarks |
| [Ling 3.0 Flash](https://meirinho.com.br/en/ia/modelos/ling-3-0-flash/)Ant Group · open | 74% | OpenRouter Benchmarks |
| [Kimi K2.5](https://meirinho.com.br/en/ia/modelos/kimi-k2-5/)Moonshot AI · open | 73.8% | OpenRouter Benchmarks |
| [MiniMax M2.7](https://meirinho.com.br/en/ia/modelos/minimax-m2-7/)MiniMax · open | 73.4% | OpenRouter Benchmarks |
| [Gemini 3 Flash Preview](https://meirinho.com.br/en/ia/modelos/gemini-3-flash-preview/)Google · undisclosed | 73.3% | OpenRouter Benchmarks |
| [GLM 4.6](https://meirinho.com.br/en/ia/modelos/glm-4-6/)Zhipu AI (Z.ai) · open | 73.3% | OpenRouter Benchmarks |
| [DeepSeek V3.1](https://meirinho.com.br/en/ia/modelos/deepseek-chat-v3-1/)DeepSeek · open | 73.1% | OpenRouter Benchmarks |
| [DeepSeek V3.1 Terminus](https://meirinho.com.br/en/ia/modelos/deepseek-v3-1-terminus/)DeepSeek · open | 73% | OpenRouter Benchmarks |
| [Gemini 3.5 Flash](https://meirinho.com.br/en/ia/modelos/gemini-3-5-flash/)Google · closed | 73% | OpenRouter Benchmarks |
| [Gemini 3.1 Flash Lite](https://meirinho.com.br/en/ia/modelos/gemini-3-1-flash-lite/)Google · closed | 72.7% | OpenRouter Benchmarks |
| [GPT-5.6 Luna](https://meirinho.com.br/en/ia/modelos/gpt-5-6-luna/)OpenAI · closed | 72.7% | OpenRouter Benchmarks |
| [GPT-6 Astra Pro](https://meirinho.com.br/en/ia/modelos/gpt-6-astra-pro/)OpenAI · undisclosed | 72.7% | OpenRouter Benchmarks |
| [Qwen3.7 Plus](https://meirinho.com.br/en/ia/modelos/qwen3-7-plus/)Alibaba · closed | 72.7% | OpenRouter Benchmarks |
| [GPT-5 Mini](https://meirinho.com.br/en/ia/modelos/gpt-5-mini/)OpenAI · closed | 72.4% | OpenRouter Benchmarks |
| [GPT-5.6 Terra](https://meirinho.com.br/en/ia/modelos/gpt-5-6-terra/)OpenAI · closed | 72.3% | OpenRouter Benchmarks |
| [Ling 3.0 Flash VL](https://meirinho.com.br/en/ia/modelos/ling-3-0-flash-vl/)Ant Group · open | 72% | OpenRouter Benchmarks |
| [Qwen3.7 Max](https://meirinho.com.br/en/ia/modelos/qwen3-7-max/)Alibaba · closed | 72% | OpenRouter Benchmarks |
| [GPT-5.6 Sol Pro](https://meirinho.com.br/en/ia/modelos/gpt-5-6-sol-pro/)OpenAI · undisclosed | 71.7% | OpenRouter Benchmarks |
| [Nemotron 3.5 Lightning](https://meirinho.com.br/en/ia/modelos/nemotron-3-5-lightning/)NVIDIA · open | 71.5% | OpenRouter Benchmarks |
| [GPT-5](https://meirinho.com.br/en/ia/modelos/gpt-5/)OpenAI · closed | 70.7% | OpenRouter Benchmarks |
| [GPT-5.6 Luna Pro](https://meirinho.com.br/en/ia/modelos/gpt-5-6-luna-pro/)OpenAI · undisclosed | 70.7% | OpenRouter Benchmarks |
| [GPT-6.1 Sol](https://meirinho.com.br/en/ia/modelos/gpt-6-1-sol/)OpenAI · closed | 70.7% | OpenRouter Benchmarks |
| [Gemma 4 26B A4B](https://meirinho.com.br/en/ia/modelos/gemma-4-26b-a4b-it/)Google · open | 70.6% | OpenRouter Benchmarks |
| [GPT-6 Sol](https://meirinho.com.br/en/ia/modelos/gpt-6-sol/)OpenAI · closed | 70.2% | OpenRouter Benchmarks |
| [GPT-6.1 Terra](https://meirinho.com.br/en/ia/modelos/gpt-6-1-terra/)OpenAI · closed | 70% | OpenRouter Benchmarks |
| [GLM 4.7 Flash](https://meirinho.com.br/en/ia/modelos/glm-4-7-flash/)Zhipu AI (Z.ai) · open | 69.7% | OpenRouter Benchmarks |
| [GPT-6 Astra](https://meirinho.com.br/en/ia/modelos/gpt-6-astra/)OpenAI · closed | 69.7% | OpenRouter Benchmarks |
| [GPT-6 Luna Pro](https://meirinho.com.br/en/ia/modelos/gpt-6-luna-pro/)OpenAI · undisclosed | 69.3% | OpenRouter Benchmarks |
| [MiniMax M2.5](https://meirinho.com.br/en/ia/modelos/minimax-m2-5/)MiniMax · open | 69.2% | OpenRouter Benchmarks |
| [GPT-6 Luna](https://meirinho.com.br/en/ia/modelos/gpt-6-luna/)OpenAI · closed | 68.4% | OpenRouter Benchmarks |
| [gpt-oss-120b](https://meirinho.com.br/en/ia/modelos/gpt-oss-120b/)OpenAI · open | 67.3% | OpenRouter Benchmarks |
| [GPT-5.4 Mini](https://meirinho.com.br/en/ia/modelos/gpt-5-4-mini/)OpenAI · closed | 66.7% | OpenRouter Benchmarks |
| [Claude Haiku 4.5](https://meirinho.com.br/en/ia/modelos/claude-haiku-4-5/)Anthropic · closed | 66.4% | OpenRouter Benchmarks |
| [GPT-5.4 Nano](https://meirinho.com.br/en/ia/modelos/gpt-5-4-nano/)OpenAI · closed | 65.6% | OpenRouter Benchmarks |
| [Granite 4.2 8B](https://meirinho.com.br/en/ia/modelos/granite-4-2-8b/)IBM · open | 64% | OpenRouter Benchmarks |
| [Qwen3 235B A22B Thinking 2507](https://meirinho.com.br/en/ia/modelos/qwen3-235b-a22b-thinking-2507/)Alibaba · open | 61.7% | OpenRouter Benchmarks |
| [GLM 4.6V](https://meirinho.com.br/en/ia/modelos/glm-4-6v/)Zhipu AI (Z.ai) · open | 60.7% | OpenRouter Benchmarks |
| [Qwen3 Coder Next](https://meirinho.com.br/en/ia/modelos/qwen3-coder-next/)Alibaba · open | 60.7% | OpenRouter Benchmarks |
| [Gemini 2.5 Pro](https://meirinho.com.br/en/ia/modelos/gemini-2-5-pro/)Google · closed | 60% | OpenRouter Benchmarks |
| [Gemini 2.5 Flash](https://meirinho.com.br/en/ia/modelos/gemini-2-5-flash/)Google · closed | 59.1% | OpenRouter Benchmarks |
| [DeepSeek R1](https://meirinho.com.br/en/ia/modelos/deepseek-r1/)DeepSeek · open | 58% | OpenRouter Benchmarks |
| [Qwen3 32B](https://meirinho.com.br/en/ia/modelos/qwen3-32b/)Alibaba · open | 54.3% | OpenRouter Benchmarks |
| [Gemini 2.5 Flash Lite](https://meirinho.com.br/en/ia/modelos/gemini-2-5-flash-lite/)Google · undisclosed | 53.7% | OpenRouter Benchmarks |
| [gpt-oss-20b](https://meirinho.com.br/en/ia/modelos/gpt-oss-20b/)OpenAI · open | 53.5% | OpenRouter Benchmarks |
| [GPT-4.1](https://meirinho.com.br/en/ia/modelos/gpt-4-1/)OpenAI · closed | 52.3% | OpenRouter Benchmarks |
| [Nemotron 3 Nano 30B A3B](https://meirinho.com.br/en/ia/modelos/nemotron-3-nano-30b-a3b/)NVIDIA · open | 52% | OpenRouter Benchmarks |
| [GPT-5 Nano](https://meirinho.com.br/en/ia/modelos/gpt-5-nano/)OpenAI · closed | 48.3% | OpenRouter Benchmarks |
| [Gemma 3 12B](https://meirinho.com.br/en/ia/modelos/gemma-3-12b-it/)Google · open | 48% | OpenRouter Benchmarks |
| [Qwen3 VL 235B A22B Instruct](https://meirinho.com.br/en/ia/modelos/qwen3-vl-235b-a22b-instruct/)Alibaba · open | 48% | OpenRouter Benchmarks |
| [Qwen3-Coder](https://meirinho.com.br/en/ia/modelos/qwen3-coder/)Alibaba · open | 48% | OpenRouter Benchmarks |
| [Qwen3-235B-A22B](https://meirinho.com.br/en/ia/modelos/qwen3-235b-a22b/)Alibaba · open | 47.9% | OpenRouter Benchmarks |
| [Qwen3 Next 80B A3B Instruct](https://meirinho.com.br/en/ia/modelos/qwen3-next-80b-a3b-instruct/)Alibaba · open | 47.5% | OpenRouter Benchmarks |
| [Qwen3 30B A3B](https://meirinho.com.br/en/ia/modelos/qwen3-30b-a3b/)Alibaba · open | 47% | OpenRouter Benchmarks |
| [Mistral Small 4](https://meirinho.com.br/en/ia/modelos/mistral-small-2603/)Mistral AI · open | 46% | OpenRouter Benchmarks |
| [Qwen3 Coder 30B A3B Instruct](https://meirinho.com.br/en/ia/modelos/qwen3-coder-30b-a3b-instruct/)Alibaba · open | 46% | OpenRouter Benchmarks |
| [GPT-4.1 Mini](https://meirinho.com.br/en/ia/modelos/gpt-4-1-mini/)OpenAI · closed | 45.1% | OpenRouter Benchmarks |
| [Qwen3 14B](https://meirinho.com.br/en/ia/modelos/qwen3-14b/)Alibaba · open | 44% | OpenRouter Benchmarks |
| [DeepSeek V3](https://meirinho.com.br/en/ia/modelos/deepseek-v3/)DeepSeek · open | 43.8% | OpenRouter Benchmarks |
| [Llama 4 Maverick](https://meirinho.com.br/en/ia/modelos/llama-4-maverick/)Meta · open | 43.4% | OpenRouter Benchmarks |
| [GPT-4o](https://meirinho.com.br/en/ia/modelos/gpt-4o/)OpenAI · closed | 43.2% | OpenRouter Benchmarks |
| [Qwen3 30B A3B Instruct 2507](https://meirinho.com.br/en/ia/modelos/qwen3-30b-a3b-instruct-2507/)Alibaba · open | 41.5% | OpenRouter Benchmarks |
| [Qwen3 VL 30B A3B Instruct](https://meirinho.com.br/en/ia/modelos/qwen3-vl-30b-a3b-instruct/)Alibaba · open | 41.3% | OpenRouter Benchmarks |
| [Llama 3.3 70B Instruct](https://meirinho.com.br/en/ia/modelos/llama-3-3-70b-instruct/)Meta · open | 39.9% | OpenRouter Benchmarks |
| [Qwen3 VL 8B Instruct](https://meirinho.com.br/en/ia/modelos/qwen3-vl-8b-instruct/)Alibaba · open | 32.7% | OpenRouter Benchmarks |
| [GPT-4o-mini](https://meirinho.com.br/en/ia/modelos/gpt-4o-mini/)OpenAI · closed | 30.7% | OpenRouter Benchmarks |
| [Qwen2.5 72B Instruct](https://meirinho.com.br/en/ia/modelos/qwen-2-5-72b-instruct/)Alibaba · open | 27.3% | OpenRouter Benchmarks |
| [Llama 3.1 8B Instruct](https://meirinho.com.br/en/ia/modelos/llama-3-1-8b-instruct/)Meta · open | 23.5% | OpenRouter Benchmarks |
| [GPT-4.1 Nano](https://meirinho.com.br/en/ia/modelos/gpt-4-1-nano/)OpenAI · closed | 14% | OpenRouter Benchmarks |

## FAQ

### Which model has the top score on τ-bench Verified (airline)?

The top score on τ-bench Verified (airline) belongs to Claude Fable 5, at 82% per OpenRouter Benchmarks. Most models are in a statistical tie with it, so the table shows the score without a rank or a badge.

### What does τ-bench Verified (airline) measure?

τ-bench Verified (airline), on the OpenRouter Benchmarks leaderboard (CC BY 4.0, latest version we checked), simulates an airline support agent that uses systems and must follow company policy until the end of the conversation. The score is the share of tasks completed within the rules.

### Which models are in this ranking?

The 130 models in this section with a published score on τ-bench Verified (airline), per OpenRouter Benchmarks. No version inherits another's score.

## How to read

1. Benchmark scores are percentages, and higher is better.
2. Rank is shown as a range, «1st of 130». Within the range, the gap to neighboring models falls within the benchmark's margin. The «top score» badge marks the model with the benchmark's top score, and the «statistical tie with the top score» badge marks models whose gap to it is within the margin.
3. On a saturated benchmark, the table shows the scores with the badge and without a rank order.

## Sources

- [Epoch AI](https://epoch.ai/benchmarks), CC BY 4.0, latest version we checked.
- [OpenRouter Benchmarks](https://openrouter.ai/benchmarks), CC BY 4.0, latest version we checked.
- [OpenRouter](https://openrouter.ai/api/v1/models), dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.

## How to cite

If you use this data, cite the page and the date you accessed it.

```
Adriano Meirinho. "τ-bench Verified (airline): AI model scores". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/benchmark/tau-bench-airline/. Accessed November 21, 2026.
```

Third-party data follows the license of each source. The full table is available as [CSV](https://meirinho.com.br/ia/modelos/dados.csv) and [JSON](https://meirinho.com.br/ia/modelos/dados.json).

[#](#)
