STT-Arena - Impossible: leaderboard
Impossible tasks, where no valid completion exists, of STT-Arena (2026), a tool-use benchmark in executable stateful environments whose conditions change in time and space during the task, with a simulated user. Pass@1 in percent (a judge must find that the agent recognized the infeasibility and told the user), mean of three runs; higher is better.
Metric: Pass@1 (%) on the 30 impossible tasks (no valid completion path exists); a task passes when a Qwen3.5-397B judge finds that the model both recognized the infeasibility and told the user; the model acts in an executable stateful environment whose state changes under scheduled spatio-temporal triggers, with a passive Qwen3.5-397B user simulator and at most 50 turns; mean of three runs at temperature 0.7; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 22 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | STT-Agent-4B (SFT+RL) | 64.44 | #324 |
| 2 | DeepSeek V3.2 | 63.33 | #425 |
| 3 | STT-Agent-4B (SFT) | 61.11 | #424 |
| 4 | Claude Sonnet 4.6 | 58.89 | #179 |
| 5 | Qwen 3.6 Plus | 54.44 | #245 |
| 6 | Gemini 3.1 Pro (Preview) | 52.22 | #102 |
| 7 | GPT-5.4 | 52.22 | #138 |
| 8 | Claude Opus 4.6 | 52.22 | #114 |
| 9 | DeepSeek V4 Pro | 45.56 | #201 |
| 10 | GLM-5 | 43.33 | #276 |
| 11 | MiniMax-M2.5 | 42.22 | #600 |
| 12 | GLM-5.1 | 41.11 | #200 |
| 13 | Kimi K2.5 | 37.78 | #272 |
| 14 | MiniMax-M2.7 | 36.67 | #539 |
| 15 | Qwen 3.5 9B | 32.22 | #838 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=stt-arena-impossible · How It Works · Data refreshed daily, snapshot 2026-11-22.