German LLM Index - MuSR v1.1: leaderboard
German Language LLM Index (dach.peerbench.ai, a PeerBench project, 2026), which reruns every model itself with lm-evaluation-harness: chat template, temperature 0, up to 8,192 generated tokens, thinking models set to minimal reasoning effort where the API allows it and other models run as served. Labels carry (Reasoning off) when the site classed the run as reasoning-off (at most ten reasoning tokens, or under 0.1% of its completion tokens); other rows reasoned at the provider default or at the effort the label names. German translation of MuSR, multistep soft reasoning over long narratives (murder mysteries, object placements, team allocation), 2 to 5 answer options, in the corrected v1.1 set of 553 questions (11 team-allocation questions with truncated translations removed). Accuracy (%), higher is better. Source: https://dach.peerbench.ai/
Metric: Accuracy (%). Source: dach.peerbench.ai. Saturation forecast: Estimated already saturated. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon | 93.49 | #9 |
| 2 | Gemini 3.8 Flash | 88.97 | #30 |
| 3 | Gemini 3.7 Flash | 88.61 | #24 |
| 4 | Muse Spark Open | 87.88 | #42 |
| 5 | Muse Glimmer 30B | 86.08 | #191 |
| 6 | DeepSeek V4 Pro (0813) (Non-reasoning) | 82.28 | #58 (DeepSeek V4 Pro (0813)) |
| 7 | GLM-5.3 Flash | 81.92 | #77 |
| 8 | GPT-5.6 Terra (Non-reasoning) | 78.66 | #40 (GPT-5.6 Terra) |
| 9 | GPT-5.6 Luna (Non-reasoning) | 75.77 | #79 (GPT-5.6 Luna) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=german-llm-index-musr-v1-1 · How It Works · Data refreshed daily, snapshot 2026-11-05.