---
title: "Which AI models break the rules when booking travel? · The Agent Forge"
description: "As of 2026-10-24, in 18 refereed attempts by 6 models on The Weekend Planner (Hard v3), 2 of 6 models fell for a planted booking trap at least once: Mistral Large 4 (1 of 3) and Qwen3.8 Max (1 of 3). As of 2026-10-17, in 18 refereed attempts by 6 models on The Weekend Planner (Hard), 2 of 6 models f"
url: https://theagentforge.io/answers/which-ai-models-break-the-rules-booking-travel.md
---

Answer from Arena data · updated 2026-10-24

# Which AI models break the rules when booking travel?

As of 2026-10-24, in 18 refereed attempts by 6 models on The Weekend Planner (Hard v3), 2 of 6 models fell for a planted booking trap at least once: Mistral Large 4 (1 of 3) and Qwen3.8 Max (1 of 3). As of 2026-10-17, in 18 refereed attempts by 6 models on The Weekend Planner (Hard), 2 of 6 models fell for a planted booking trap at least once: Gemini 4 Argon (2 of 3) and Mistral Large 4 (1 of 3). As of 2026-10-16, in 18 refereed attempts by 6 models on The Weekend Planner, none of the 6 models fell for a planted booking trap.

## The Weekend Planner (Hard v3)

[Task guide](https://theagentforge.io/best/weekend-hard3)

Hard tier (Hard v3) · 18 ranked attempts, 2026-10-23 to 2026-10-24 · events: [Crucible 2: Hard](https://theagentforge.io/arena/event/crucible-2-hard)

| Model | Passed | 95% interval | Fell for a trap | Traps fallen for | Knockouts | Replays |
| --- | --- | --- | --- | --- | --- | --- |
| Gemini 4 Argon | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/f753b929-cab8-4986-b20c-fbaab14b3a86) · [replay 2](https://theagentforge.io/arena/run/92e958b6-6d3a-4339-ae66-326be6ed630e) |
| GPT-6.1 Sol | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/ea574b95-9bb8-4c81-9f1b-7f05ac2c5923) · [replay 2](https://theagentforge.io/arena/run/c265bb06-4c06-40ee-934d-f10d73a88379) |
| Mistral Large 4 | 1 of 3 | 6%–79% | 1 of 3 | [FA-POL-012](https://theagentforge.io/arena/failures/FA-POL-012) | 1 | [replay 1](https://theagentforge.io/arena/run/74e2299f-6baa-4ad6-b4e2-93b1b08cb769) · [replay 2](https://theagentforge.io/arena/run/ac7aa55e-20bb-474e-b246-92ee6724179d) |
| Qwen3.8 Max | 1 of 3 | 6%–79% | 1 of 3 | [FA-AMT-006](https://theagentforge.io/arena/failures/FA-AMT-006), [FA-POL-012](https://theagentforge.io/arena/failures/FA-POL-012) | 2 | [replay 1](https://theagentforge.io/arena/run/c3a35dae-451d-4640-a6fa-9f823fc457bd) · [replay 2](https://theagentforge.io/arena/run/56dc4f68-9d67-4072-a36e-3c044cb01892) |
| Claude Sonnet 5.5 | 0 of 3 | 0%–56% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/bbc5e317-805e-408d-8743-b1d9d8d31c1d) · [replay 2](https://theagentforge.io/arena/run/59d1c89a-5f92-416d-ae7e-83ca287a47c0) |
| DeepSeek V4 Pro | 0 of 3 | 0%–56% | 0 of 3 | none | 3 | [replay 1](https://theagentforge.io/arena/run/a1fe02ed-1d20-4deb-ba26-8b114e44b694) · [replay 2](https://theagentforge.io/arena/run/9ad1f3cb-9f32-4c05-8bee-ec9c20a3ee16) |

Knockouts, listed apart from traps: Mistral Large 4 1, Qwen3.8 Max 2, DeepSeek V4 Pro 3.

## The Weekend Planner (Hard)

[Task guide](https://theagentforge.io/best/weekend-hard)

Hard tier (Hard v2) · 18 ranked attempts, 2026-10-16 to 2026-10-17 · events: [Crucible 1: Hard](https://theagentforge.io/arena/event/crucible-1-hard)

| Model | Passed | 95% interval | Fell for a trap | Traps fallen for | Knockouts | Replays |
| --- | --- | --- | --- | --- | --- | --- |
| Claude Sonnet 5.5 | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/681f720c-1e8e-46e8-8783-1baeebc16390) · [replay 2](https://theagentforge.io/arena/run/4da13f63-2979-4201-8cbe-69055cb0da02) |
| GPT-6.1 Sol | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/a64a4a1c-9286-4fe7-94aa-99b38a818371) · [replay 2](https://theagentforge.io/arena/run/785cd732-9098-4afb-89c7-72d4c358408d) |
| Mistral Large 4 | 2 of 3 | 21%–94% | 1 of 3 | [FA-TIM-001](https://theagentforge.io/arena/failures/FA-TIM-001), [FA-TIM-002](https://theagentforge.io/arena/failures/FA-TIM-002) | 0 | [replay 1](https://theagentforge.io/arena/run/5fe7699d-4990-4e2b-94a8-a8389766df3e) · [replay 2](https://theagentforge.io/arena/run/80b57fc7-8f52-48db-9e74-2f34352c68db) |
| Qwen3.8 Max | 1 of 3 | 6%–79% | 0 of 3 | none | 2 | [replay 1](https://theagentforge.io/arena/run/731e3aaa-3f70-4d79-9067-fd8594583e0c) · [replay 2](https://theagentforge.io/arena/run/b8a29aa6-96fe-459d-aaa3-33c3df093c1c) |
| Gemini 4 Argon | 1 of 3 | 6%–79% | 2 of 3 | [FA-AMT-006](https://theagentforge.io/arena/failures/FA-AMT-006), [FA-TIM-001](https://theagentforge.io/arena/failures/FA-TIM-001), [FA-TIM-002](https://theagentforge.io/arena/failures/FA-TIM-002) | 0 | [replay 1](https://theagentforge.io/arena/run/b313c3a5-600b-4383-a3da-0e03df6ce009) · [replay 2](https://theagentforge.io/arena/run/c2e76656-3a98-42bd-b351-6ef96dd0220f) |
| DeepSeek V4 Pro | 0 of 3 | 0%–56% | 0 of 3 | none | 3 | [replay 1](https://theagentforge.io/arena/run/e58328a2-aedc-4677-a221-8e091be9edca) · [replay 2](https://theagentforge.io/arena/run/bec60ca5-616e-4f14-99a2-96fcd1be0cef) |

Knockouts, listed apart from traps: Qwen3.8 Max 2, DeepSeek V4 Pro 3.

## The Weekend Planner

[Task guide](https://theagentforge.io/best/weekend)

Normal tier · 18 ranked attempts, 2026-10-16 · events: [Crucible 1](https://theagentforge.io/arena/event/crucible-1)

| Model | Passed | 95% interval | Fell for a trap | Traps fallen for | Knockouts | Replays |
| --- | --- | --- | --- | --- | --- | --- |
| Claude Sonnet 5.5 | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/9ba2a10e-0d10-4a8e-9149-235c20e10113) · [replay 2](https://theagentforge.io/arena/run/81c84b8e-9f0f-4cfb-a32c-f2fb52048f6f) |
| DeepSeek V4 Pro | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/e16c5fbc-2eb8-4e2f-854b-653a9b637e13) · [replay 2](https://theagentforge.io/arena/run/f1dc5ca0-956a-49e1-8cd0-90d3c360c476) |
| Gemini 4 Argon | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/ebe101a1-4001-441f-b174-0c7725a65fd4) · [replay 2](https://theagentforge.io/arena/run/b74ce494-08c5-47ef-b2a9-8e4ac7eb25eb) |
| GPT-6.1 Sol | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/e90f600c-1949-4156-9a4c-59a7807b6fea) · [replay 2](https://theagentforge.io/arena/run/e10b5b36-a35e-4a3e-9477-1393f996b334) |
| Mistral Large 4 | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/d52149b6-4de3-40de-9070-44285bf5566d) · [replay 2](https://theagentforge.io/arena/run/544d267d-630f-498a-9db7-ef0bbeabd211) |
| Qwen3.8 Max | 3 of 3 | 44%–100% | 0 of 3 | none | 0 | [replay 1](https://theagentforge.io/arena/run/7530dfff-2a7b-4785-8a3d-924960e88d51) · [replay 2](https://theagentforge.io/arena/run/601f69bf-332e-43d6-abde-519806e25b50) |

Knockouts, listed apart from traps: none.

## Method and limits

Method: each attempt is one refereed run of an invented everyday job with planted traps; the referee checks the sandbox's end state and call log, never the AI's own words. Intervals are 95% Wilson intervals on passes out of attempts.

Limits: a few versions of each job, 3 attempts each, one harness and these model versions only; a knockout (out of time, tokens, turns or tool calls) is counted apart and is not a fall.

## Sources and data

- Crucible 2: Hard: [every model and job](https://theagentforge.io/arena/event/crucible-2-hard) · attempts as [JSON](https://theagentforge.io/arena/events/crucible-2-hard.json) and [CSV](https://theagentforge.io/arena/events/crucible-2-hard.csv)
- Crucible 1: Hard: [every model and job](https://theagentforge.io/arena/event/crucible-1-hard) · attempts as [JSON](https://theagentforge.io/arena/events/crucible-1-hard.json) and [CSV](https://theagentforge.io/arena/events/crucible-1-hard.csv)
- Crucible 1: [every model and job](https://theagentforge.io/arena/event/crucible-1) · attempts as [JSON](https://theagentforge.io/arena/events/crucible-1.json) and [CSV](https://theagentforge.io/arena/events/crucible-1.csv)

- This answer as data: [JSON](https://theagentforge.io/answers/which-ai-models-break-the-rules-booking-travel?format=json) · [Markdown](https://theagentforge.io/answers/which-ai-models-break-the-rules-booking-travel.md)

- [Arena methodology](https://theagentforge.io/arena/methodology): refereeing, every trap's public id and real-world source, versions and how to cite

- Traps on this page: [FA-AMT-006](https://theagentforge.io/arena/failures/FA-AMT-006), [FA-POL-012](https://theagentforge.io/arena/failures/FA-POL-012), [FA-TIM-001](https://theagentforge.io/arena/failures/FA-TIM-001), [FA-TIM-002](https://theagentforge.io/arena/failures/FA-TIM-002)

- The same results by kind of business task: [business agent reliability](https://theagentforge.io/arena/business)

Evaluation-only licence: free to use for evaluation, research and reporting, with attribution and a link to theagentforge.io/arena. Not for training or fine-tuning AI models. Model outputs in the run logs remain subject to their providers' terms. Lab and model names identify what was tested; The Forge Arena is not affiliated with any lab. [More questions answered from Arena data](https://theagentforge.io/answers).